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
    forme
    -0.06
    �
    -0.06
     Propel
    -0.06
     Hearing
    -0.06
     rapor
    -0.06
     专
    -0.06
     помощи
    -0.06
     천
    -0.06
    flatten
    -0.06
    éric
    -0.06
    POSITIVE LOGITS
    ше
    0.07
     الحر
    0.06
    |=
    0.06
     MQ
    0.06
     suche
    0.06
    ��글
    0.06
     रहत
    0.06
     XI
    0.06
    っていた
    0.06
    razy
    0.06
    Act Density 0.000%

    No Known Activations