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

    Neuronpedia

    INDEX
    Explanations

    unstable API changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comments
    -0.06
     starvation
    -0.06
     ZERO
    -0.06
     موسیقی
    -0.06
     transcription
    -0.06
     investigación
    -0.06
     enjoyable
    -0.06
     child
    -0.06
     uniq
    -0.06
    كرة
    -0.06
    POSITIVE LOGITS
    �
    0.07
    而
    0.07
    ��
    0.06
     universally
    0.06
    �
    0.06
    -enabled
    0.06
     permanent
    0.06
    programs
    0.06
    qx
    0.06
     obl
    0.06
    Act Density 0.008%

    No Known Activations