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

    Neuronpedia

    INDEX
    Explanations

    list of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ActivityResult
    -0.07
     di
    -0.07
    RSS
    -0.07
    -cond
    -0.07
    Pack
    -0.06
     Cry
    -0.06
     day
    -0.06
    HAVE
    -0.06
     coursework
    -0.06
     aggregation
    -0.06
    POSITIVE LOGITS
     overl
    0.07
    eden
    0.07
    letters
    0.07
    _poly
    0.06
     experi
    0.06
    >{$
    0.06
     позитив
    0.06
     fø
    0.06
     WON
    0.06
     ridiculously
    0.06
    Act Density 0.008%

    No Known Activations