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

    Neuronpedia

    INDEX
    Explanations

    ~

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cliffs
    -0.07
    countries
    -0.07
    亲密
    -0.07
    逍
    -0.07
    -padding
    -0.07
    <Event
    -0.07
    Barrier
    -0.07
    IEEE
    -0.06
    _MR
    -0.06
    笾
    -0.06
    POSITIVE LOGITS
    当て
    0.07
    ificação
    0.06
    buch
    0.06
     flashlight
    0.06
    .gz
    0.06
    -->
↵
    0.06
    leich
    0.06
     Hose
    0.06
    さ
    0.06
    ']=$
    0.06
    Act Density 0.000%

    No Known Activations