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

    Neuronpedia

    INDEX
    Explanations

    Computer hardware and drivers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aç
    -0.07
     đoán
    -0.07
     федера
    -0.07
     Date
    -0.07
    Liverpool
    -0.06
     dans
    -0.06
    CommandLine
    -0.06
    زد
    -0.06
     smb
    -0.06
    災
    -0.06
    POSITIVE LOGITS
     interceptor
    0.06
     Residence
    0.06
     Willie
    0.06
     wiel
    0.06
    	res
    0.06
    /he
    0.06
    ,T
    0.06
    ANGER
    0.05
    ,f
    0.05
     chop
    0.05
    Act Density 0.037%

    No Known Activations