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

    Neuronpedia

    INDEX
    Explanations

    names of characters and complex syllables

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

    Indian language suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的一部分
    -0.41
    шная
    -0.40
    iconque
    -0.40
     geniales
    -0.40
    الإنجليزية
    -0.37
     इसका
    -0.37
    nutie
    -0.37
    Pherson
    -0.37
    Enumerator
    -0.37
     beauty
    -0.37
    POSITIVE LOGITS
     वाले
    0.56
    ले
    0.54
    ने
    0.53
    لے
    0.53
    disposing
    0.52
    PerformLayout
    0.52
    વા
    0.52
    GenerationType
    0.51
    ના
    0.47
    ड़े
    0.47
    Act Density 0.007%

    No Known Activations