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

    Neuronpedia

    INDEX
    Explanations

    instinct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fudge
    -0.08
     alku
    -0.08
     المستوى
    -0.08
     pai
    -0.08
    対象
    -0.08
    单位
    -0.08
     obtenido
    -0.08
     parent's
    -0.08
    一般
    -0.07
    Количество
    -0.07
    POSITIVE LOGITS
     Bedür
    0.09
     unfold
    0.08
     unfolding
    0.08
     krä
    0.08
     burgeoning
    0.08
    gie
    0.08
     unfolds
    0.08
    _ss
    0.08
     är
    0.07
     unveiling
    0.07
    Act Density 0.086%

    No Known Activations