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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables that summarize or illustrate data and findings

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

    figure shows or illustrates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſte
    -0.59
     ſta
    -0.58
     ſche
    -0.54
     ſtre
    -0.53
     Anſ
    -0.52
    IsMutable
    -0.52
     Permalink
    -0.51
     ſtate
    -0.50
     ſch
    -0.50
    ſelf
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.52
     snippetHide
    0.47
     relâche
    0.42
    RTLI
    0.42
     sicht
    0.41
     shown
    0.38
     незавершена
    0.38
     verwijzen
    0.37
    áklad
    0.37
     <=",
    0.36
    Act Density 0.205%

    No Known Activations