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

    Neuronpedia

    INDEX
    Explanations

    XML or HTML-like strings and markup elements related to user interface components

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

    string name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indígen
    -0.52
     asesinado
    -0.48
     Comprometido
    -0.48
     Lingkungan
    -0.47
     equipamiento
    -0.47
     izquier
    -0.46
     inmigrantes
    -0.46
     maquinaria
    -0.45
     lentejuelas
    -0.45
     increí
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.55
    farer
    0.54
     Atom
    0.54
    CVS
    0.52
    carpa
    0.51
    pok
    0.50
    roc
    0.50
    obel
    0.48
     BLS
    0.48
    alos
    0.48
    Act Density 0.099%

    No Known Activations