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

    Neuronpedia

    INDEX
    Explanations

    max function call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    පා
    0.84
    ου
    0.80
    твы
    0.78
    йдет
    0.78
     RCMP
    0.77
     Jeddah
    0.76
     ruthless
    0.75
     fief
    0.75
    пы
    0.73
    жды
    0.73
    POSITIVE LOGITS
    ين
    0.75
    Cooper
    0.75
     उत्तर
    0.73
    此之外
    0.73
    Hay
    0.72
    ਾਰ
    0.71
    نة
    0.71
    ಇದ
    0.70
    Greg
    0.68
     \{\
    0.68
    Act Density 0.007%

    No Known Activations