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

    Neuronpedia

    INDEX
    Explanations

    Irritation or trigger for an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intimidating
    0.52
    垢
    0.49
     upped
    0.48
     surpassed
    0.48
    mapping
    0.47
     greeted
    0.47
     abruptly
    0.47
     anxieties
    0.47
    bucket
    0.47
     fishes
    0.46
    POSITIVE LOGITS
    Status
    0.55
    Society
    0.50
     Vereinigten
    0.50
    \
    0.49
    Provence
    0.48
     Ararat
    0.48
     Bör
    0.48
    ABAB
    0.47
    ARD
    0.46
    Lind
    0.46
    Act Density 0.000%

    No Known Activations