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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and positivity

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

    verb followed by adverb or pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     investissements
    -0.39
     Trá
    -0.38
     cinturón
    -0.38
     campaña
    -0.37
     onResponse
    -0.37
    ScopeManager
    -0.36
     amenazas
    -0.35
    AnimationsModule
    -0.35
    ]--;
    -0.35
     suel
    -0.35
    POSITIVE LOGITS
    oplayer
    0.49
    COUVER
    0.47
     censiti
    0.46
     Capture
    0.45
     JADX
    0.42
     VIDEOTAPE
    0.41
     Administrativna
    0.41
     EOF
    0.41
     wireType
    0.39
     Biôgrafia
    0.39
    Act Density 0.145%

    No Known Activations