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

    Neuronpedia

    INDEX
    Explanations

    life history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stalking
    -0.07
    нин
    -0.06
     /^\
    -0.06
    carousel
    -0.06
    져
    -0.06
    ский
    -0.06
     buộc
    -0.06
     '?
    -0.06
    inging
    -0.06
    Images
    -0.06
    POSITIVE LOGITS
    .Alert
    0.07
     Net
    0.07
     Contract
    0.07
    Tot
    0.07
    _PERSON
    0.06
    _COST
    0.06
    -mark
    0.06
    .Render
    0.06
    Tonight
    0.06
    Laugh
    0.06
    Act Density 0.034%

    No Known Activations