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

    Neuronpedia

    INDEX
    Explanations

    boolean values in logical comparisons

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

    truth of statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.35
     själva
    -0.32
     Masyarakat
    -0.32
     Kegiatan
    -0.31
    bleib
    -0.31
    ülerin
    -0.31
     Sementara
    -0.30
    ={({
    -0.30
    ötzlich
    -0.30
     élector
    -0.29
    POSITIVE LOGITS
     True
    0.78
     true
    0.75
    True
    0.75
     TRUE
    0.73
    TRUE
    0.71
    true
    0.69
     False
    0.68
     untrue
    0.66
    false
    0.65
     false
    0.64
    Act Density 0.156%

    No Known Activations