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

    Neuronpedia

    INDEX
    Explanations

    professional effective control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    其他
    0.57
    MAN
    0.55
    MER
    0.49
    CL
    0.48
    Cap
    0.48
    ደጋ
    0.48
    на
    0.47
    MON
    0.46
    MAS
    0.46
    涷
    0.46
    POSITIVE LOGITS
     ကြ
    0.50
     tokamak
    0.48
    ธิ
    0.47
     magnetic
    0.46
    ellik
    0.46
    äck
    0.45
     متخصص
    0.45
     physicians
    0.44
     lässt
    0.44
     कां
    0.43
    Act Density 0.000%

    No Known Activations