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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '\
    -0.07
    42
    -0.06
    /ws
    -0.06
     forget
    -0.06
    _tag
    -0.06
     peg
    -0.06
    -label
    -0.06
    _threads
    -0.06
     понять
    -0.06
     bites
    -0.06
    POSITIVE LOGITS
    pollo
    0.07
    备注
    0.06
     пох
    0.06
     سر
    0.06
    .StatusCode
    0.06
     takeover
    0.06
     управ
    0.06
    .Iter
    0.06
    _Component
    0.06
    очные
    0.06
    Act Density 0.005%

    No Known Activations