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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific formatting symbols

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

    code punctuation separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    schirm
    -0.41
     always
    -0.40
     really
    -0.40
     suces
    -0.39
    Quién
    -0.39
     Singapura
    -0.38
     sure
    -0.36
    GrantedAuthority
    -0.36
     صاد
    -0.35
    getSelectedItem
    -0.35
    POSITIVE LOGITS
    RepeatedField
    0.56
    UnknownFields
    0.54
    AnchorStyles
    0.54
    '}),
    0.53
     للمعارف
    0.53
     dAtA
    0.52
     ویکی‌پدی
    0.50
    الإنجليزية
    0.50
    Autoritní
    0.50
     considérons
    0.49
    Act Density 0.003%

    No Known Activations