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

    Neuronpedia

    INDEX
    Explanations

    one-to-one relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parton
    0.48
    ignant
    0.46
    gene
    0.45
    brane
    0.45
     甘
    0.45
    gado
    0.44
     ডাক
    0.44
    maso
    0.44
    set
    0.44
    niveau
    0.44
    POSITIVE LOGITS
     Mercedes
    0.48
     CHARLES
    0.47
    AVES
    0.47
     M
    0.46
     MM
    0.46
     affairs
    0.46
     cocktails
    0.46
     odre
    0.46
     ami
    0.45
     championships
    0.45
    Act Density 0.001%

    No Known Activations