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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stripe
    -0.06
     Earl
    -0.06
     gaat
    -0.06
    Alice
    -0.06
    상품
    -0.06
     Levi
    -0.06
     Mood
    -0.06
     adrenaline
    -0.06
    22
    -0.06
     soon
    -0.06
    POSITIVE LOGITS
    _METHOD
    0.08
     approaches
    0.07
    不是
    0.07
     as
    0.07
     hash
    0.07
     at
    0.07
    orphism
    0.07
     OS
    0.06
     avatar
    0.06
    _CONTROLLER
    0.06
    Act Density 0.017%

    No Known Activations