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

    Neuronpedia

    INDEX
    Explanations

    discussions about technical difficulties and potential solutions in practical scenarios

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

    cannot do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -1.02
    aarrggbb
    -0.98
     مشين
    -0.89
    ArrowToggle
    -0.82
    RegistryLite
    -0.81
    ThroughAttribute
    -0.78
     autorytatywna
    -0.75
    LookAnd
    -0.75
    setVerticalGroup
    -0.75
     nahilalakip
    -0.73
    POSITIVE LOGITS
     cannot
    0.84
     impractical
    0.81
     impossible
    0.71
     impracticable
    0.68
     unavailable
    0.66
    cannot
    0.63
     couldn
    0.62
     inaccessible
    0.61
     unable
    0.60
    impossible
    0.56
    Act Density 0.497%

    No Known Activations