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

    Neuronpedia

    INDEX
    Explanations

    numbers and sums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    postcode
    -0.07
    Programming
    -0.07
     gode
    -0.07
    АН
    -0.07
    YT
    -0.07
    GetY
    -0.06
    ण
    -0.06
     PP
    -0.06
    _corr
    -0.06
     Firewall
    -0.06
    POSITIVE LOGITS
    /ac
    0.06
     引
    0.06
    풍
    0.06
     ignoring
    0.06
    writing
    0.06
     Amit
    0.06
    _dropout
    0.06
     دخ
    0.06
    _aff
    0.06
    ').'
    0.06
    Act Density 0.009%

    No Known Activations