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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    心脏
    -0.08
     thrift
    -0.07
    итет
    -0.07
    טא
    -0.07
    /exp
    -0.06
    .where
    -0.06
    >L
    -0.06
    .kafka
    -0.06
    '(
    -0.06
    [href
    -0.06
    POSITIVE LOGITS
     widać
    0.07
    逆袭
    0.07
     począ
    0.07
     �
    0.07
    	in
    0.07
    kom
    0.06
    _SUPER
    0.06
    “↵↵
    0.06
    IRON
    0.06
    toInt
    0.06
    Act Density 0.004%

    No Known Activations