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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize clarity, significance, or understanding in various contexts

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

    all so/very X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COMERC
    -0.42
     PHOSPH
    -0.41
     szóci
    -0.40
     naselje
    -0.40
     conmigo
    -0.39
     PartialEq
    -0.39
     jabatan
    -0.39
     statistic
    -0.38
    imach
    -0.38
     menak
    -0.38
    POSITIVE LOGITS
    SaveChangesAsync
    0.65
    everything
    0.65
     everything
    0.61
     alles
    0.58
    Всё
    0.58
     Everything
    0.57
    Everything
    0.57
     tudo
    0.54
    的一切
    0.52
     protoimpl
    0.50
    Act Density 0.109%

    No Known Activations