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

    Neuronpedia

    INDEX
    Explanations

    terms related to visibility and display status in a user interface

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

    hidden, concealed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yce
    -0.51
    raeli
    -0.47
    それで
    -0.46
     Jule
    -0.44
    maksud
    -0.43
     useDispatch
    -0.43
    VolleyError
    -0.41
    yakarta
    -0.41
    製品
    -0.41
     Meksiku
    -0.41
    POSITIVE LOGITS
    hidden
    2.28
    Hidden
    2.19
     Hidden
    2.17
     hidden
    2.17
    HIDDEN
    1.84
     verborgen
    1.49
    隐藏
    1.38
     HID
    1.34
     concealed
    1.34
    isHidden
    1.33
    Act Density 0.006%

    No Known Activations