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

    Neuronpedia

    INDEX
    Explanations

    your task is to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     replicas
    0.26
     jeder
    0.22
    screenshot
    0.22
     des
    0.21
    ရန်
    0.21
    log
    0.20
     log
    0.20
     logarithm
    0.20
     fijn
    0.19
    sed
    0.19
    POSITIVE LOGITS
     confers
    0.20
     Judiciary
    0.20
     Gubern
    0.19
    ERICK
    0.19
     indoct
    0.19
     przeciw
    0.18
    𓃵
    0.18
     çoc
    0.18
     scholarly
    0.18
    крови
    0.18
    Act Density 0.070%

    No Known Activations