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

    Neuronpedia

    INDEX
    Explanations

    court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elerden
    -0.07
    439
    -0.06
     "="
    -0.06
    私は
    -0.06
     기억
    -0.06
     atas
    -0.06
    _PHASE
    -0.06
    .configure
    -0.06
     içi
    -0.06
    율
    -0.06
    POSITIVE LOGITS
     Attachment
    0.07
     เจ
    0.07
    wing
    0.07
    SL
    0.06
     skewed
    0.06
    navigation
    0.06
     прин
    0.06
    	sys
    0.06
    lett
    0.06
     salon
    0.06
    Act Density 0.014%

    No Known Activations