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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

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

    prior to adoption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hyrchwyd
    -0.46
    Personensuche
    -0.38
    Coordonnées
    -0.34
    }}}
    -0.33
     peix
    -0.33
    ölkerung
    -0.32
     विश्वसनीयता
    -0.32
     ObjectParameter
    -0.32
     recibido
    -0.31
    miljø
    -0.31
    POSITIVE LOGITS
    TagMode
    0.50
     ब्रेकडाउन
    0.48
     تكبرها
    0.46
     IBRARY
    0.46
    yarnpkg
    0.45
    ViewImports
    0.44
    DebuggerNonUser
    0.44
     linkovi
    0.41
     المعيارى
    0.41
    点此举报
    0.41
    Act Density 0.402%

    No Known Activations