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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _disc
    -0.07
     де
    -0.07
    _TH
    -0.07
     Oz
    -0.06
    опас
    -0.06
    Educ
    -0.06
     dich
    -0.06
    Rad
    -0.06
    -wing
    -0.06
    .Sc
    -0.06
    POSITIVE LOGITS
     hide
    0.06
     aliment
    0.06
    amoto
    0.06
    rame
    0.06
    vie
    0.06
    __)↵
    0.06
     messing
    0.06
     kern
    0.06
    ış
    0.06
     sistema
    0.06
    Act Density 0.000%

    No Known Activations