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

    Neuronpedia

    INDEX
    Explanations

    names and titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indication
    -0.08
     squat
    -0.07
     unten
    -0.07
     conv
    -0.07
     harmed
    -0.07
     навер
    -0.07
    ecer
    -0.07
    ourcem
    -0.07
    .addListener
    -0.07
    ργ
    -0.06
    POSITIVE LOGITS
    _EXECUTE
    0.06
     muh
    0.06
    ////////////////////////////////////////////////////////////////////////////////
    0.06
    crets
    0.06
    -selected
    0.06
    ฮ
    0.06
    signed
    0.06
    .isNull
    0.05
     elseif
    0.05
    tie
    0.05
    Act Density 0.013%

    No Known Activations