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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     스트
    -0.08
     Вас
    -0.06
    entanyl
    -0.06
     Retrieve
    -0.06
    VAR
    -0.06
    'Re
    -0.06
     Anc
    -0.06
    _SUFFIX
    -0.06
    (___
    -0.06
    verture
    -0.06
    POSITIVE LOGITS
    .url
    0.07
    .PERMISSION
    0.07
    observation
    0.07
     possessions
    0.06
    �
    0.06
     oriented
    0.06
    ุ่
    0.06
     açık
    0.06
    ideon
    0.06
    動
    0.06
    Act Density 0.007%

    No Known Activations