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

    Neuronpedia

    INDEX
    Explanations

    dictates content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valuations
    0.44
    valued
    0.43
     복
    0.42
     комплекса
    0.41
    tape
    0.40
    Gesellschaft
    0.40
    valuation
    0.40
     certiorari
    0.40
     komplex
    0.40
     reductions
    0.39
    POSITIVE LOGITS
     TouchUtils
    0.51
    accès
    0.49
     distant
    0.44
     बताये
    0.44
    途径
    0.42
    敌人
    0.41
     pedibus
    0.41
     ligação
    0.40
     ໃນ
    0.40
     Tk
    0.39
    Act Density 0.044%

    No Known Activations