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

    Neuronpedia

    INDEX
    Explanations

    statistical results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getString
    -0.07
    isation
    -0.06
    dados
    -0.06
     lô
    -0.06
    	f
    -0.06
     sweaty
    -0.06
    _phi
    -0.06
    865
    -0.06
    abeth
    -0.06
     lun
    -0.06
    POSITIVE LOGITS
     说
    0.06
    
    0.06
     Pokémon
    0.06
    _MSK
    0.06
    itemap
    0.06
     ""){↵
    0.06
     ''){↵
    0.06
    季
    0.06
    容
    0.06
    (sock
    0.06
    Act Density 0.015%

    No Known Activations