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

    Neuronpedia

    INDEX
    Explanations

    player

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the player‐character (e.g. the word “player” or “character”) in Unity 2D C# script requests.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _received
    -0.07
    Nut
    -0.07
    .Dialog
    -0.06
    uffman
    -0.06
     abducted
    -0.06
    _GRID
    -0.06
    ΜΑΤ
    -0.06
     Nut
    -0.06
     greenhouse
    -0.06
    distinct
    -0.06
    POSITIVE LOGITS
     ((*
    0.07
    äl
    0.07
    ━�
    0.06
     دام
    0.06
     initialValue
    0.06
     ----------------------------------------------------------------------------↵
    0.06
    τερ
    0.06
     ι
    0.06
     sánh
    0.06
     vyvol
    0.06
    Act Density 0.007%

    No Known Activations