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

    Neuronpedia

    INDEX
    Explanations

    run migrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Philosophy
    0.47
     uporab
    0.45
    lovepoetry
    0.43
    ፈላ
    0.41
     neuropathy
    0.40
    Arcs
    0.40
     angla
    0.40
     schizophren
    0.40
     reductase
    0.40
    лосо
    0.40
    POSITIVE LOGITS
     Determine
    0.67
     Display
    0.63
     Determines
    0.63
     Initializes
    0.61
     Gets
    0.60
     Indicates
    0.59
     Executes
    0.58
     determine
    0.58
     Get
    0.56
     determines
    0.56
    Act Density 0.010%

    No Known Activations