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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and symbols related to addition and subtraction

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

    mathematical or code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.66
     HasFactory
    -0.60
    ########.
    -0.60
     surla
    -0.60
     queſta
    -0.55
    amom
    -0.54
    ſelf
    -0.54
     Biôgrafia
    -0.52
    alone
    -0.52
    évaluateur
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.43
     ratusan
    0.40
     pouvoit
    0.38
     înc
    0.37
     rağmen
    0.36
     yanı
    0.35
     advertencia
    0.35
     lámpara
    0.35
     oscuridad
    0.34
    hermoso
    0.34
    Act Density 0.157%

    No Known Activations