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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heten
    -0.07
    ']])↵
    -0.07
     اساس
    -0.06
    。↵↵↵↵
    -0.06
     lov
    -0.06
    _p
    -0.06
     процес
    -0.06
    (Adapter
    -0.06
     Mg
    -0.06
     '/../
    -0.06
    POSITIVE LOGITS
     Pitt
    0.06
     thaw
    0.06
     thieves
    0.06
    410
    0.06
     algorithms
    0.06
     pdb
    0.06
     développement
    0.06
    building
    0.06
     preventing
    0.06
    ClassLoader
    0.06
    Act Density 0.000%

    No Known Activations