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

    Neuronpedia

    INDEX
    Explanations

    borrowing and returning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σμού
    -0.07
     Tài
    -0.06
     futile
    -0.06
     poate
    -0.06
    _truth
    -0.06
     outreach
    -0.06
     木
    -0.06
    _ER
    -0.06
    _fm
    -0.06
    ря
    -0.06
    POSITIVE LOGITS
     encompass
    0.07
     "\",
    0.07
     خص
    0.06
     advantage
    0.06
     Anch
    0.06
    .ModelForm
    0.06
     "',
    0.06
     asleep
    0.06
     replicas
    0.06
    .Unmarshal
    0.06
    Act Density 0.006%

    No Known Activations