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

    Neuronpedia

    INDEX
    Explanations

    resources and extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ur
    0.61
    ল
    0.49
    on
    0.48
    ர்
    0.48
    ان
    0.47
    نا
    0.46
    as
    0.45
    all
    0.44
    color
    0.44
    Fat
    0.44
    POSITIVE LOGITS
     reina
    0.52
     convient
    0.50
     refrigerant
    0.48
    に適
    0.48
     მან
    0.45
    適
    0.45
     собе
    0.45
     Cher
    0.44
    に移
    0.44
     indis
    0.44
    Act Density 0.002%

    No Known Activations