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

    Neuronpedia

    INDEX
    Explanations

    fixing things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شاخ
    -0.08
    [to
    -0.07
    azard
    -0.07
     transcripts
    -0.06
    ارية
    -0.06
     LENGTH
    -0.06
    (.
    -0.06
    เย
    -0.06
    aed
    -0.06
    GLOSS
    -0.06
    POSITIVE LOGITS
     genç
    0.06
    �
    0.06
    ующ
    0.06
    /cli
    0.06
     ConcurrentHashMap
    0.06
    -edit
    0.06
    -options
    0.06
     coveted
    0.06
    Segue
    0.06
     Horde
    0.06
    Act Density 0.193%

    No Known Activations