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

    Neuronpedia

    INDEX
    Explanations

    baking/cooking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    direct
    -0.07
     Крім
    -0.07
     Evalu
    -0.07
    Project
    -0.07
    Increasing
    -0.07
     Countdown
    -0.07
    arius
    -0.06
     Louise
    -0.06
     cathedral
    -0.06
    rient
    -0.06
    POSITIVE LOGITS
     ers
    0.07
    .Dot
    0.06
     老
    0.06
     cps
    0.06
    /plugin
    0.06
    .ra
    0.06
    účast
    0.06
     �
    0.06
     joked
    0.06
    394
    0.06
    Act Density 0.006%

    No Known Activations