Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash

    statements about the emotional and physical states of a character in a game.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on the numeric status values in the character‐state report (the decimal numbers following each attribute label).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    호
    -0.07
    َأ
    -0.07
     heel
    -0.07
     Vaults
    -0.06
    .Att
    -0.06
    CU
    -0.06
    �
    -0.06
    ||
    -0.06
    -pl
    -0.06
    ritos
    -0.06
    POSITIVE LOGITS
    )*
    0.07
    )*(
    0.07
    derive
    0.07
    ))*
    0.06
     blízk
    0.06
    地
    0.06
     هنگام
    0.06
    /nginx
    0.06
     carrera
    0.06
    <Class
    0.06
    Act Density 0.039%

    No Known Activations