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

    Neuronpedia

    INDEX
    Explanations

    favorites

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enerative
    -0.07
    .setInput
    -0.07
     bekan
    -0.07
    .email
    -0.07
    /train
    -0.07
     tau
    -0.06
     Democrat
    -0.06
    	Client
    -0.06
     african
    -0.06
    unted
    -0.06
    POSITIVE LOGITS
     更
    0.06
     accuracy
    0.06
    _userid
    0.06
    ливий
    0.05
    	range
    0.05
    (pl
    0.05
    -либо
    0.05
    addtogroup
    0.05
     chẳng
    0.05
    America
    0.05
    Act Density 0.129%

    No Known Activations