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

    Neuronpedia

    INDEX
    Explanations

    script tag following template

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FLAG
    0.41
     FLAG
    0.41
     Lobster
    0.41
     WORK
    0.39
     lobster
    0.39
     Oph
    0.38
     någon
    0.37
     gross
    0.37
     FLOOR
    0.36
    గొ
    0.35
    POSITIVE LOGITS
    urst
    0.40
    pathy
    0.39
    Theorem
    0.39
     Theorem
    0.38
    unton
    0.38
    ᖃ
    0.38
    வான
    0.38
    ాలయ
    0.38
     Rejo
    0.37
     traditional
    0.36
    Act Density 0.001%

    No Known Activations