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

    Neuronpedia

    INDEX
    Explanations

    Cha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pred
    -0.06
     CPU
    -0.06
     conducive
    -0.06
    ;s
    -0.06
    wood
    -0.06
     hybrid
    -0.06
     Abr
    -0.06
     windows
    -0.06
     plugged
    -0.05
     frequency
    -0.05
    POSITIVE LOGITS
     машин
    0.08
    нять
    0.08
    -ob
    0.07
     وضعیت
    0.07
    .INVALID
    0.07
    /github
    0.07
    (vc
    0.07
     車
    0.07
     dialogRef
    0.07
     ابراه
    0.07
    Act Density 0.004%

    No Known Activations