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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    libraries
    -0.07
     fds
    -0.07
    _items
    -0.06
     Wenn
    -0.06
     Castillo
    -0.06
     Loy
    -0.06
    Detector
    -0.06
     jeep
    -0.06
    atcher
    -0.06
    _EMAIL
    -0.06
    POSITIVE LOGITS
     reflecting
    0.07
     undocumented
    0.07
     endurance
    0.06
     fundraising
    0.06
    GeV
    0.06
    ochond
    0.06
    *******
↵
    0.06
     gameState
    0.06
    center
    0.06
     corresponding
    0.06
    Act Density 0.006%

    No Known Activations