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

    Neuronpedia

    INDEX
    Explanations

    Code and data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vec
    -0.07
     notre
    -0.07
    _tC
    -0.06
    nof
    -0.06
    났다
    -0.06
     Ε
    -0.06
    <TResult
    -0.06
     ullam
    -0.06
    اذا
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _phone
    0.06
     Netanyahu
    0.06
     disemb
    0.06
     atmos
    0.06
    Merge
    0.06
    Float
    0.06
    现场
    0.06
     політи
    0.06
    _ComCallableWrapper
    0.06
    핑
    0.06
    Act Density 0.000%

    No Known Activations