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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge, secrets, or hidden information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hidden or guarded locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sklici
    -0.54
    endmodule
    -0.45
    fromnode
    -0.44
    Gön
    -0.40
    RegistryLite
    -0.40
    qrstuvwxyz
    -0.38
    GeoNames
    -0.37
    Brainz
    -0.37
    Посилання
    -0.36
     esc
    -0.35
    POSITIVE LOGITS
     незавершена
    0.53
     renfer
    0.52
    yelidikan
    0.42
    offsetTop
    0.41
    bestos
    0.40
    hidden
    0.39
     tesoro
    0.39
     محفوظة
    0.39
     unlock
    0.38
     trove
    0.38
    Act Density 0.359%

    No Known Activations