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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    य
    -0.07
    (mac
    -0.07
    Effect
    -0.07
     prv
    -0.06
     Sour
    -0.06
    ء
    -0.06
    混
    -0.06
    _OBS
    -0.06
    �情
    -0.06
    _RIGHT
    -0.06
    POSITIVE LOGITS
     repreh
    0.08
    cin
    0.06
    uento
    0.06
    acements
    0.06
    δο
    0.06
     inoc
    0.06
     nib
    0.06
    ={'
    0.06
     despre
    0.06
     pione
    0.06
    Act Density 0.082%

    No Known Activations