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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    زا
    -0.07
     зат
    -0.07
    itched
    -0.06
    ui
    -0.06
    eti
    -0.06
     floats
    -0.06
     ancor
    -0.06
    elle
    -0.06
    lify
    -0.06
    toFloat
    -0.06
    POSITIVE LOGITS
     Farmer
    0.07
    .Errorf
    0.06
    .separator
    0.06
    .pages
    0.06
    による
    0.06
     миним
    0.06
     şirket
    0.06
     tộc
    0.06
     sus
    0.06
     上
    0.06
    Act Density 0.227%

    No Known Activations