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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ává
    -0.08
    ências
    -0.07
    ilateral
    -0.07
    isches
    -0.07
     gd
    -0.07
     merge
    -0.07
     beings
    -0.06
    (short
    -0.06
    hibition
    -0.06
    ैद
    -0.06
    POSITIVE LOGITS
    Chef
    0.07
    .toLocale
    0.06
     alarming
    0.06
     começ
    0.06
    .observe
    0.06
     interes
    0.06
    .preview
    0.06
    extracomment
    0.06
     pret
    0.06
    /g
    0.06
    Act Density 0.006%

    No Known Activations