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

    Neuronpedia

    INDEX
    Explanations

    terms related to matrix numerical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    res / android / resource

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.57
     almohada
    -0.54
    ToBounds
    -0.52
    ientôt
    -0.52
    ToFit
    -0.52
    Blanco
    -0.50
     Público
    -0.50
    áneamente
    -0.50
     ainfi
    -0.49
     Capitán
    -0.49
    POSITIVE LOGITS
    res
    2.63
     res
    2.06
    Res
    1.70
     Res
    1.69
    RES
    1.66
     RES
    1.30
    ARES
    1.09
    eres
    1.09
    resu
    1.08
    ares
    1.06
    Act Density 0.012%

    No Known Activations