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

    Neuronpedia

    INDEX
    Explanations

    specify parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bertson
    0.68
    很重要
    0.65
     хозяй
    0.64
     exhort
    0.63
    사는
    0.62
     edildi
    0.59
     perceives
    0.59
     bukanlah
    0.59
    が発生
    0.57
     सर्वप्रथम
    0.57
    POSITIVE LOGITS
     параметра
    0.71
    ":"
    0.68
     "\
    0.67
     "-"
    0.66
     especificar
    0.66
     "=
    0.64
     "").
    0.64
     "(
    0.62
     Specify
    0.62
     Örneğin
    0.62
    Act Density 0.003%

    No Known Activations