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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and math formatting

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

    cohomology theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.54
     houſe
    -0.47
     ſur
    -0.47
     ſtate
    -0.46
     raiſ
    -0.43
     ſtre
    -0.42
     purpoſe
    -0.41
     diſt
    -0.41
     neceſſ
    -0.41
     ſche
    -0.40
    POSITIVE LOGITS
    endphp
    0.61
    anthes
    0.55
    BibitemShut
    0.54
    ']=='
    0.53
     함께
    0.53
     The
    0.52
    :]:
    0.52
    ValueStyle
    0.51
    InThe
    0.51
    ectoria
    0.50
    Act Density 0.004%

    No Known Activations