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

    Neuronpedia

    INDEX
    Explanations

    quoted text delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Graduation
    0.82
     Tired
    0.81
    ли
    0.80
    كل
    0.80
    ك
    0.80
    gambar
    0.78
    過去
    0.77
     probleme
    0.76
     sores
    0.75
    kräft
    0.75
    POSITIVE LOGITS
    pier
    0.73
     сеть
    0.73
    зовая
    0.71
     junto
    0.70
     {...
    0.70
     subray
    0.70
     acerca
    0.69
     alqu
    0.66
    Mess
    0.65
     принял
    0.65
    Act Density 0.003%

    No Known Activations