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

    Neuronpedia

    INDEX
    Explanations

    characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clases
    -0.07
     ironic
    -0.06
    PLY
    -0.06
    cheid
    -0.06
    ायत
    -0.06
    _Helper
    -0.06
    @example
    -0.06
     dee
    -0.06
     museums
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Comments
    0.08
    ―
    0.07
    (Stream
    0.07
    010
    0.06
     jedn
    0.06
     astronomers
    0.06
     pin
    0.06
    मन
    0.06
    мар
    0.06
     confront
    0.06
    Act Density 0.015%

    No Known Activations