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

    Neuronpedia

    INDEX
    Explanations

    Dodging/evading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erra
    -0.06
     since
    -0.06
     salope
    -0.06
    _fa
    -0.06
     beast
    -0.06
    astics
    -0.06
    ládání
    -0.06
     triệu
    -0.06
    oni
    -0.06
    '/>
    -0.06
    POSITIVE LOGITS
    parse
    0.07
    меж
    0.07
     předpok
    0.07
     câu
    0.06
     boolean
    0.06
     undef
    0.06
     Phân
    0.06
    Schema
    0.06
     Cong
    0.06
    Cong
    0.06
    Act Density 0.012%

    No Known Activations