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

    Neuronpedia

    INDEX
    Explanations

    Key Skills and Apply Dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    唓
    0.40
    ்கலை
    0.39
    ێ
    0.39
     złoż
    0.37
     dowol
    0.37
     seleção
    0.37
    ieß
    0.37
     competición
    0.37
     oposición
    0.36
     abhängig
    0.36
    POSITIVE LOGITS
    <eos>
    0.48
    KEY
    0.36
    7
    0.35
    5
    0.35
     Facebook
    0.34
     Hemos
    0.34
    6
    0.34
     Keywords
    0.34
    祝
    0.33
    ಕ್ಕು
    0.33
    Act Density 0.000%

    No Known Activations