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

    Neuronpedia

    INDEX
    Explanations

    account suspension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ling
    0.45
    ol
    0.45
    atu
    0.44
    icen
    0.44
     Ashwin
    0.44
    al
    0.43
    oran
    0.43
    atio
    0.43
    musik
    0.43
    ora
    0.42
    POSITIVE LOGITS
     áreas
    0.46
     defensa
    0.46
    Defense
    0.46
     Après
    0.46
     normalcy
    0.46
     athletic
    0.45
     santé
    0.45
     privé
    0.44
     área
    0.44
     compréhension
    0.44
    Act Density 0.005%

    No Known Activations