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

    Neuronpedia

    INDEX
    Explanations

    patterns of numbers or codes

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

    Alphanumeric characters followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal strings or ids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.79
    apimachinery
    -0.75
    BeginInit
    -0.70
     Majefty
    -0.69
    Personendaten
    -0.68
    Попис
    -0.67
     Borel
    -0.67
     infinitive
    -0.66
     ſind
    -0.66
     perſon
    -0.66
    POSITIVE LOGITS
     gynhyrchwyd
    0.56
    awaiter
    0.55
     typelib
    0.54
     nahilalakip
    0.54
     Infórmanos
    0.51
     Савезне
    0.49
    ästi
    0.45
     ***!
    0.44
     <<<<<<<<<<<<<<
    0.43
    bmatrix
    0.43
    Act Density 0.113%

    No Known Activations