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

    Neuronpedia

    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уляр
    -0.07
    alling
    -0.06
    _inches
    -0.06
    Far
    -0.06
     magically
    -0.06
    ์ร
    -0.06
    ीएम
    -0.06
    ілі
    -0.06
    %f
    -0.06
     far
    -0.06
    POSITIVE LOGITS
     tasar
    0.07
     protect
    0.07
     RIP
    0.07
     bisa
    0.06
    invoices
    0.06
    /event
    0.06
    	NdrFcShort
    0.06
    영어
    0.06
     توسعه
    0.06
     stools
    0.06
    Act Density 0.070%

    No Known Activations