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

    Neuronpedia

    INDEX
    Explanations

    camel's back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     startActivity
    0.41
    RefIn
    0.40
    PolicyQuery
    0.38
     conceivable
    0.38
    修炼
    0.38
     повышение
    0.37
     legis
    0.37
     regelmäßig
    0.37
    畱
    0.37
     mungkin
    0.36
    POSITIVE LOGITS
    isted
    0.43
    ack
    0.41
    but
    0.40
    isting
    0.39
     but
    0.39
    ukov
    0.39
    acker
    0.38
    acked
    0.38
     detailed
    0.38
    detailed
    0.37
    Act Density 0.000%

    No Known Activations