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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that indicate procedural instructions or advice

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

    end of sentence delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.71
     Roskov
    -0.57
     ModelExpression
    -0.57
     AssemblyCulture
    -0.54
    DockStyle
    -0.52
    ConstraintMaker
    -0.52
    ſt
    -0.50
     Autorizaciones
    -0.50
     pleaſure
    -0.50
    جستارهای
    -0.48
    POSITIVE LOGITS
    <eos>
    0.51
    pena
    0.39
     Италијани
    0.36
    ">'+
    0.35
    رشف
    0.33
     الرياضيه
    0.33
    ]`
    0.32
    こち
    0.31
    0.30
    Breath
    0.30
    Act Density 0.013%

    No Known Activations