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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tertiary
    -0.07
    ｍ
    -0.07
    му
    -0.06
    .ReadKey
    -0.06
    atory
    -0.06
    διο
    -0.06
     calidad
    -0.06
     valor
    -0.06
    šel
    -0.06
    '>{
    -0.06
    POSITIVE LOGITS
    ));↵↵↵
    0.07
     düzenlenen
    0.06
     Cooling
    0.06
    umpy
    0.06
     укра
    0.06
    ikers
    0.06
    knowledge
    0.06
     лишь
    0.06
    Frequency
    0.06
    าง
    0.06
    Act Density 0.006%

    No Known Activations