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

    Neuronpedia

    INDEX
    Explanations

    Technical/Informational writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     może
    -0.07
     případech
    -0.07
     pierws
    -0.06
    .video
    -0.06
     herhangi
    -0.06
     wię
    -0.06
     zajím
    -0.06
     UIP
    -0.06
     payouts
    -0.06
     Minecraft
    -0.06
    POSITIVE LOGITS
    Soft
    0.07
    YST
    0.07
     Arch
    0.06
     Soft
    0.06
    antage
    0.06
    ServerError
    0.06
    oft
    0.06
     Celebration
    0.06
    *scale
    0.06
    enty
    0.06
    Act Density 0.211%

    No Known Activations