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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Axis
    -0.07
    542
    -0.06
    760
    -0.06
    ümüş
    -0.06
    (sign
    -0.06
    232
    -0.06
    6
    -0.06
    ovém
    -0.06
    loom
    -0.06
    ової
    -0.06
    POSITIVE LOGITS
     Erdogan
    0.07
    _Syntax
    0.07
    wav
    0.07
    -duration
    0.07
     Мініст
    0.07
    _exit
    0.06
     всп
    0.06
     peers
    0.06
    .instructions
    0.06
    _Current
    0.06
    Act Density 0.001%

    No Known Activations