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

    Neuronpedia

    INDEX
    Explanations

    disclaimers or disclosures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shrew
    0.84
     umbilical
    0.83
     perpetuated
    0.79
     amyg
    0.79
     però
    0.78
     большую
    0.77
     anthrac
    0.75
     verfol
    0.75
     starb
    0.75
     satta
    0.75
    POSITIVE LOGITS
    ERICK
    0.71
    Р
    0.71
    ersion
    0.70
    ifs
    0.70
    ികി
    0.70
    rence
    0.69
    ÉS
    0.68
    يلات
    0.68
    鸽
    0.67
    avasena
    0.66
    Act Density 0.156%

    No Known Activations