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

    Neuronpedia

    INDEX
    Explanations

    risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hugs
    -0.07
    -eyed
    -0.07
     نحو
    -0.07
     využí
    -0.07
     Cock
    -0.06
     vap
    -0.06
     hazır
    -0.06
    ，无
    -0.06
    Player
    -0.06
     Thankfully
    -0.06
    POSITIVE LOGITS
     prostitution
    0.07
     COR
    0.06
    routing
    0.06
    (SP
    0.06
    \F
    0.06
    Univers
    0.06
    ILING
    0.06
    fq
    0.06
    (ds
    0.06
    heatmap
    0.06
    Act Density 0.016%

    No Known Activations