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

    Neuronpedia

    INDEX
    Explanations

    formation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alance
    -0.08
    -ins
    -0.08
    Bracket
    -0.08
    -negative
    -0.08
    OLUME
    -0.08
    -webpack
    -0.08
     recursos
    -0.08
    _addresses
    -0.07
    _inside
    -0.07
    /apimachinery
    -0.07
    POSITIVE LOGITS
     noisy
    0.11
     corrupted
    0.11
     noise
    0.10
     corrupt
    0.10
     contaminated
    0.09
    Noise
    0.09
     Noise
    0.09
    Simulator
    0.09
     corruption
    0.09
     manifestations
    0.09
    Act Density 0.015%

    No Known Activations