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

    Neuronpedia

    INDEX
    Explanations

    geometry problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ystä
    -0.09
     mood
    -0.09
    异常
    -0.08
     fjöl
    -0.08
     UUID
    -0.08
     diversity
    -0.08
    Scripts
    -0.08
     emotions
    -0.07
     shuffled
    -0.07
     jede
    -0.07
    POSITIVE LOGITS
     nestled
    0.09
     smaller
    0.09
    _INS
    0.09
     Smaller
    0.08
     carved
    0.08
     sogen
    0.08
     southwestern
    0.08
     maximizing
    0.08
    -bottom
    0.08
    .Bottom
    0.08
    Act Density 0.038%

    No Known Activations