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

    Neuronpedia

    INDEX
    Explanations

    configuration settings parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dahin
    0.39
     spontaneously
    0.38
     tragic
    0.38
    equity
    0.38
    იმ
    0.37
     concluir
    0.37
     Havel
    0.37
     fakta
    0.37
    ataya
    0.37
    phthalm
    0.36
    POSITIVE LOGITS
     настройки
    1.77
     settings
    1.74
     configurable
    1.67
     parameters
    1.62
     Settings
    1.61
    settings
    1.58
    Settings
    1.54
     настрой
    1.54
     adjustable
    1.52
     customization
    1.49
    Act Density 0.100%

    No Known Activations