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

    Neuronpedia

    INDEX
    Explanations

    references to additional entities or subjects in context

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

    and others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()",
    -0.35
    ')")
    -0.35
    GenerationType
    -0.35
    "])
    -0.35
    })=
    -0.34
    DebuggerStep
    -0.33
     INDEPENDENT
    -0.33
    )))),
    -0.33
    ']==
    -0.33
    ジュアル
    -0.33
    POSITIVE LOGITS
    Others
    1.59
     Others
    1.54
     others
    1.53
    others
    1.52
     OTHERS
    1.40
    OTHERS
    1.17
     دیگران
    0.87
    其他人
    0.84
     אחרים
    0.78
    antaranya
    0.73
    Act Density 0.012%

    No Known Activations