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

    Neuronpedia

    INDEX
    Explanations

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quota
    -0.07
    ibe
    -0.07
     Sommer
    -0.07
    Pe
    -0.06
    oust
    -0.06
     histogram
    -0.06
    chr
    -0.06
     costume
    -0.06
     appearances
    -0.06
    nu
    -0.06
    POSITIVE LOGITS
     Наг
    0.07
     masturb
    0.06
     přem
    0.06
     كرد
    0.06
     Би
    0.06
    疆
    0.06
    InMillis
    0.06
     masturbating
    0.06
    Unused
    0.06
     ketogenic
    0.06
    Act Density 0.062%

    No Known Activations