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

    Neuronpedia

    INDEX
    Explanations

    prominent political figures and related political terms

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

    Anwar Ibrahim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wireType
    -0.36
     akurat
    -0.35
     arcilla
    -0.35
    éndole
    -0.34
    ándote
    -0.34
     quedado
    -0.33
    schwar
    -0.33
     glú
    -0.33
    identical
    -0.32
     ladrillo
    -0.32
    POSITIVE LOGITS
    riwal
    0.84
    Życiorys
    0.65
    tinyos
    0.59
    casio
    0.54
    aarrggbb
    0.52
     Jefus
    0.50
     poveznice
    0.49
    şört
    0.49
     оригіналу
    0.48
    InputTagHelper
    0.47
    Act Density 0.085%

    No Known Activations