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

    Neuronpedia

    INDEX
    Explanations

    ChatGPT Plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apresentação
    1.02
     feitas
    1.02
     importante
    1.01
     sangue
    0.97
     Slice
    0.97
     boton
    0.97
     adaptador
    0.96
    ␊
    0.96
     datos
    0.96
     ہوتے
    0.95
    POSITIVE LOGITS
    دون
    0.83
    及其
    0.83
    ków
    0.80
    ли
    0.79
    JH
    0.78
     profoundly
    0.74
    ರ
    0.74
    をはじめ
    0.73
     बघेल
    0.73
    으며
    0.72
    Act Density 0.444%

    No Known Activations