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

    Neuronpedia

    INDEX
    Explanations

    Character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hab
    -0.07
     Raiders
    -0.07
     зависит
    -0.07
    _ID
    -0.06
     东
    -0.06
     Moreover
    -0.06
    ten
    -0.06
    -0.06
    na
    -0.06
    ND
    -0.06
    POSITIVE LOGITS
     Character
    0.14
    character
    0.14
    (character
    0.13
     characters
    0.13
    .character
    0.12
    .Character
    0.12
     CHARACTER
    0.12
    (Character
    0.12
    _characters
    0.11
     character
    0.10
    Act Density 0.013%

    No Known Activations