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

    Neuronpedia

    INDEX
    Explanations

    references to external links or resources for further information

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

    see the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.73
    parsedMessage
    -0.59
    Дереккөздер
    -0.58
    下载附件
    -0.56
    الحياه
    -0.55
     ब्रेकडाउन
    -0.54
     Infórmanos
    -0.54
    PCell
    -0.53
     MainAxisSize
    -0.52
     utafitiHapana
    -0.52
    POSITIVE LOGITS
     the
    0.61
     our
    0.46
     murni
    0.37
    lindungi
    0.37
     his
    0.36
     cromado
    0.34
     같은
    0.33
    published
    0.33
     Kapitel
    0.33
    ++)
    0.32
    Act Density 0.018%

    No Known Activations