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

    Neuronpedia

    INDEX
    Explanations

    trade-offs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ances
    0.93
    iances
    0.90
    aches
    0.89
    ings
    0.89
     off
    0.85
    ständig
    0.84
    nings
    0.79
    messages
    0.78
    wamy
    0.77
    ANCES
    0.77
    POSITIVE LOGITS
    IBM
    0.78
     düzenlenen
    0.70
     elektrol
    0.70
    圭
    0.70
    纤维
    0.70
    Organiz
    0.70
     aprov
    0.69
     поступи
    0.69
     faltando
    0.68
     erforderlich
    0.67
    Act Density 0.002%

    No Known Activations