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

    Neuronpedia

    INDEX
    Explanations

    significance, breaks, male, contact, Wire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    But
    0.86
    That
    0.85
     Over
    0.84
    So
    0.84
    Με
    0.82
    Over
    0.80
    Не
    0.80
    Па
    0.79
    Well
    0.79
    但是
    0.79
    POSITIVE LOGITS
    jších
    0.86
     lengthwise
    0.79
    LPTMR
    0.78
    lei
    0.75
    jí
    0.75
     машиналарын
    0.75
    товых
    0.74
    jším
    0.74
     tablespoon
    0.74
     myriad
    0.73
    Act Density 0.003%

    No Known Activations