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

    Neuronpedia

    INDEX
    Explanations

    Mathematical equations symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     εί
    -0.08
     Cage
    -0.07
     PCA
    -0.07
    _OC
    -0.06
    _CUR
    -0.06
     Android
    -0.06
    installer
    -0.06
    )//
    -0.06
     PUS
    -0.06
    IRM
    -0.06
    POSITIVE LOGITS
    .panel
    0.06
    earning
    0.06
    ocious
    0.06
    viol
    0.06
    -small
    0.06
    apr
    0.06
     spraying
    0.06
     weaken
    0.05
    ublik
    0.05
     neat
    0.05
    Act Density 0.015%

    No Known Activations