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

    Neuronpedia

    INDEX
    Explanations

    assertive statements about beliefs or speculations

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

    Questions with uncertain or vague answers

    np_acts-logits-general · gemini-2.0-flash

    was it, or something?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.58
     titolata
    -0.52
    WriteBarrier
    -0.49
    awtextra
    -0.48
     '\\;'
    -0.44
    InputBorder
    -0.43
    脚注の使い方
    -0.43
    addGap
    -0.43
    PYX
    -0.43
    Pyx
    -0.42
    POSITIVE LOGITS
     alguma
    0.46
     somewhere
    0.44
     alguna
    0.44
     ModelExpression
    0.44
    (?)
    0.44
     (?)
    0.44
     idk
    0.43
    好像是
    0.42
    ?)
    0.42
     maybe
    0.41
    Act Density 0.366%

    No Known Activations