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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )|
    -0.07
    Sign
    -0.07
    ive
    -0.07
    _Password
    -0.07
     disrupted
    -0.07
    'Re
    -0.07
    mozilla
    -0.06
     uploader
    -0.06
     agrees
    -0.06
    .'/'.$
    -0.06
    POSITIVE LOGITS
    -option
    0.07
     Josef
    0.07
     Sized
    0.06
     Celtics
    0.06
     innate
    0.06
    .clients
    0.06
     ص
    0.06
     تهیه
    0.06
     proudly
    0.06
     primer
    0.06
    Act Density 0.000%

    No Known Activations