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

    Neuronpedia

    INDEX
    Explanations

    distances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .”
    -0.07
    cape
    -0.07
    ."
    -0.06
    -button
    -0.06
    hill
    -0.06
    ,”
    -0.06
    lucent
    -0.06
     Daniels
    -0.06
    会议
    -0.06
    dif
    -0.06
    POSITIVE LOGITS
     Tata
    0.08
     MSR
    0.07
    сок
    0.06
    海
    0.06
     Lockheed
    0.06
    receiver
    0.06
    'Re
    0.06
     ومن
    0.06
    _MASK
    0.06
    プリ
    0.06
    Act Density 0.007%

    No Known Activations