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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.08
     performers
    -0.07
    andidates
    -0.07
     border
    -0.07
    զ
    -0.07
    வர்கள்
    -0.07
     tendencia
    -0.07
     nagh
    -0.07
     bepalen
    -0.07
    သား
    -0.07
    POSITIVE LOGITS
    Observed
    0.09
     кезінде
    0.09
     observed
    0.08
    ographed
    0.08
    "When
    0.08
     видно
    0.08
    Alternate
    0.08
     amikor
    0.08
     senere
    0.08
    'inc
    0.08
    Act Density 0.055%

    No Known Activations