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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "hidden" in various contexts

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

    hidden things and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conmigo
    -0.59
    jetunion
    -0.49
     Welle
    -0.48
    anjutnya
    -0.48
     Reihe
    -0.47
    บ้าง
    -0.47
    ogues
    -0.46
     useAppContext
    -0.46
     Anura
    -0.46
     TRABAJO
    -0.46
    POSITIVE LOGITS
     hidden
    1.63
     Hidden
    1.45
    Hidden
    1.30
    hidden
    1.08
    HIDDEN
    1.04
     verborgen
    0.99
     concealed
    0.98
     HID
    0.94
     oculto
    0.92
    隐藏
    0.91
    Act Density 0.008%

    No Known Activations