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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate the quality, importance, or origin of things

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scip
    -0.63
    Personensuche
    -0.55
    ]='\
    -0.51
     Mlle
    -0.51
     semblait
    -0.50
     therewith
    -0.50
    sobí
    -0.50
     ат
    -0.50
     scurt
    -0.49
     tevens
    -0.49
    POSITIVE LOGITS
    مصادر
    0.77
    Hochspringen
    0.65
     inputs
    0.63
    PyTuple
    0.63
    SOUNDBITE
    0.59
    <bos>
    0.59
     indisponible
    0.56
    saraba
    0.56
    SBATCH
    0.56
    deed
    0.56
    Act Density 2.149%

    No Known Activations