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

    Neuronpedia

    INDEX
    Explanations

    initialization constructor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     를
    -0.08
    halte
    -0.08
     горяч
    -0.08
     Tank
    -0.08
     Fleet
    -0.08
     ಅರ್�
    -0.08
     welt
    -0.08
     Fili
    -0.08
     بالك
    -0.08
     мн
    -0.07
    POSITIVE LOGITS
    时期
    0.08
     مرحلة
    0.08
    NSData
    0.08
    邦
    0.08
     indirect
    0.08
     marks
    0.08
     indirectly
    0.07
    Ex
    0.07
     etapa
    0.07
     painters
    0.07
    Act Density 0.000%

    No Known Activations