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

    Neuronpedia

    INDEX
    Explanations

    scientific research articles

    oai_token-act-pair · gemini-2.0-flash

    Cancer research and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slightly
    -0.75
     completamente
    -0.73
    completely
    -0.71
     completely
    -0.71
     totalmente
    -0.66
    Slightly
    -0.65
    slightly
    -0.65
     Completely
    -0.64
     Slightly
    -0.63
    Completely
    -0.63
    POSITIVE LOGITS
     sign
    0.73
    abestanden
    0.72
     дописавши
    0.68
    Sign
    0.60
     disappoint
    0.57
    DllImport
    0.56
    NameInMap
    0.55
     Sign
    0.54
     signe
    0.54
     disgust
    0.54
    Act Density 9.098%

    No Known Activations