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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and their variations

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

    Korvayan says

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gy
    -0.47
    gasse
    -0.44
    gespräch
    -0.44
    textEdit
    -0.43
     Italijani
    -0.43
    geschenk
    -0.43
    萩
    -0.43
    ẹo
    -0.43
     himo
    -0.43
     poly
    -0.42
    POSITIVE LOGITS
    mcn
    0.76
    en
    0.72
    ian
    0.72
    nen
    0.71
    nnnn
    0.71
    ccn
    0.69
    xan
    0.69
    eden
    0.69
    nnn
    0.68
    an
    0.68
    Act Density 1.463%

    No Known Activations