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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .datasets
    -0.07
     Player
    -0.07
    _PROXY
    -0.06
    Richard
    -0.06
     picnic
    -0.06
     آ
    -0.06
    이어
    -0.06
     구성
    -0.06
    _font
    -0.06
     deployed
    -0.06
    POSITIVE LOGITS
     indem
    0.06
     Του
    0.06
    ل
    0.06
     ticking
    0.06
    เฉล
    0.06
    KV
    0.06
    doubleValue
    0.06
    �
    0.06
    企
    0.06
     panoramic
    0.06
    Act Density 0.138%

    No Known Activations