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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helper
    -0.07
     महत
    -0.06
    .handler
    -0.06
    usc
    -0.06
    bt
    -0.06
    aso
    -0.06
    	not
    -0.06
     sails
    -0.06
    =name
    -0.06
     blanco
    -0.06
    POSITIVE LOGITS
    .magic
    0.07
     soluble
    0.06
     شده
    0.06
     Superman
    0.06
     able
    0.06
     करन
    0.06
     Effective
    0.06
    інь
    0.06
     certify
    0.06
    ��
    0.06
    Act Density 0.018%

    No Known Activations