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

    Neuronpedia

    INDEX
    Explanations

    diff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Codigo
    -0.07
    уется
    -0.06
     halde
    -0.06
     Palo
    -0.06
     Valentine
    -0.06
     Shack
    -0.06
     ItemType
    -0.06
     Kot
    -0.05
    -chair
    -0.05
     novamente
    -0.05
    POSITIVE LOGITS
     diff
    0.07
     corro
    0.07
    .transforms
    0.07
    affected
    0.07
     mitochondrial
    0.07
     directional
    0.06
    ाध
    0.06
    _modal
    0.06
    _diff
    0.06
    	success
    0.06
    Act Density 0.004%

    No Known Activations