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

    Neuronpedia

    INDEX
    Explanations

    javascript configuration files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuisses
    0.49
    胸
    0.48
    Насе
    0.46
    螂
    0.45
    ƾ
    0.44
    ቑ
    0.43
     PDPN
    0.42
    丷
    0.42
     சுண்ணாம்பு
    0.42
     வெள்ளி
    0.42
    POSITIVE LOGITS
     parserOptions
    0.76
    extends
    0.73
    parser
    0.71
     env
    0.68
    over
    0.66
    env
    0.66
    root
    0.64
     extends
    0.64
     ecmaVersion
    0.64
     over
    0.63
    Act Density 0.002%

    No Known Activations