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

    Neuronpedia

    INDEX
    Explanations

    references to accompanying figures, tables, or examples in a document

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

    figures, appendices, or other sections

    np_acts-logits-general · gemini-2.0-flash

    referencing sections or external information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Itself
    -0.58
    LookAnd
    -0.55
    andExpect
    -0.53
     onely
    -0.52
    assertThat
    -0.51
     öyle
    -0.51
    Xna
    -0.48
    看上去
    -0.47
     MwSt
    -0.47
    contentLoaded
    -0.47
    POSITIVE LOGITS
     http
    1.03
     below
    0.96
     https
    0.96
     attached
    0.88
     www
    0.86
     Appendix
    0.84
     previous
    0.83
    below
    0.79
     appendix
    0.74
    http
    0.74
    Act Density 0.655%

    No Known Activations