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

    Neuronpedia

    INDEX
    Explanations

    CISSP, CFA certifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.81
     CH
    0.71
     is
    0.70
    스
    0.66
    8
    0.66
     B
    0.66
     H
    0.64
     Fig
    0.63
     v
    0.62
     this
    0.62
    POSITIVE LOGITS
    чены
    0.75
    ěr
    0.72
    ᱔
    0.70
    ز
    0.69
     लाव
    0.68
    ą
    0.68
    çou
    0.67
     часу
    0.66
    èdent
    0.65
    èces
    0.64
    Act Density 0.001%

    No Known Activations