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

    Neuronpedia

    INDEX
    Explanations

    a and important

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belts
    -0.06
    zzo
    -0.06
    ssp
    -0.06
     absl
    -0.06
    ety
    -0.06
    .Components
    -0.06
    StringLength
    -0.06
    weeney
    -0.06
    ्रमण
    -0.06
    achinery
    -0.06
    POSITIVE LOGITS
     自
    0.07
     Орг
    0.07
    ，再
    0.06
     лок
    0.06
     Neb
    0.06
    物理
    0.06
     отнош
    0.06
    +s
    0.06
    斷
    0.06
    (loss
    0.06
    Act Density 0.045%

    No Known Activations