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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     державної
    -0.07
     rewritten
    -0.07
     burada
    -0.07
    remain
    -0.06
    Dead
    -0.06
     dbl
    -0.06
     Hiring
    -0.06
    _ctr
    -0.06
     �
    -0.06
     όπου
    -0.06
    POSITIVE LOGITS
     densities
    0.07
     scans
    0.07
    Audio
    0.07
     Italian
    0.07
     salvation
    0.06
     swing
    0.06
     Jelly
    0.06
     companies
    0.06
    τρα
    0.06
     padded
    0.06
    Act Density 0.000%

    No Known Activations