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

    Neuronpedia

    INDEX
    Explanations

    FOR IMMEDIATE RELEASE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fore
    0.58
    fore
    0.54
     Fore
    0.52
    Fore
    0.49
    FORE
    0.47
    Тем
    0.39
     NIL
    0.39
     heterozygous
    0.38
     nicotin
    0.38
     forearm
    0.38
    POSITIVE LOGITS
    bes
    0.64
    BES
    0.61
    rester
    0.57
    rest
    0.54
    bés
    0.50
    بس
    0.49
    Bes
    0.45
    rests
    0.43
    besch
    0.43
    बे
    0.43
    Act Density 0.004%

    No Known Activations