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

    Neuronpedia

    INDEX
    Explanations

    -of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetSize
    -0.07
     �
    -0.07
     setError
    -0.07
     Lug
    -0.06
     curs
    -0.06
     '%'
    -0.06
     takım
    -0.06
     November
    -0.06
    Similarly
    -0.06
     refuses
    -0.06
    POSITIVE LOGITS
    _Enc
    0.07
    นา
    0.06
    _ai
    0.06
    reater
    0.06
     音
    0.06
    oust
    0.06
    ����
    0.06
    してい
    0.05
    .sequence
    0.05
    >]
    0.05
    Act Density 0.088%

    No Known Activations