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

    Neuronpedia

    INDEX
    Explanations

    inserting code or into contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.56
    to
    0.53
    ta
    0.52
     box
    0.52
    box
    0.50
    ex
    0.49
     text
    0.48
    od
    0.47
     blind
    0.47
    ok
    0.46
    POSITIVE LOGITS
     gamanam
    0.62
    棈
    0.55
    jenje
    0.53
    hamton
    0.52
    闶
    0.52
    वेलकम
    0.51
    लाब
    0.50
     adquis
    0.50
     ذریع
    0.50
     উপন
    0.50
    Act Density 0.000%

    No Known Activations