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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARM
    -0.67
    arm
    -0.62
     #
    -0.51
    ram
    -0.50
     news
    -0.48
     $\
    -0.46
     pem
    -0.46
     Head
    -0.44
     +
    -0.44
     @
    -0.43
    POSITIVE LOGITS
     itſelf
    1.13
    ſelf
    1.05
    ſelves
    0.99
    Personensuche
    0.98
    InputBorder
    0.98
     myſelf
    0.98
    nastics
    0.97
     مرئيه
    0.94
     виправивши
    0.94
    Datuak
    0.92
    Act Density 0.631%

    No Known Activations