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

    Neuronpedia

    INDEX
    Explanations

    providing context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evaluates
    -0.07
     боку
    -0.07
     blends
    -0.07
    Black
    -0.07
     herself
    -0.06
     himself
    -0.06
     масла
    -0.06
     Particle
    -0.06
     Nacht
    -0.06
    ющими
    -0.06
    POSITIVE LOGITS
     št
    0.07
    ermalink
    0.06
    (record
    0.06
     Sür
    0.06
     مذ
    0.06
    rgctx
    0.06
    _SAMPLES
    0.06
     adulte
    0.06
     إلي
    0.06
    itempty
    0.06
    Act Density 0.090%

    No Known Activations