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

    Neuronpedia

    INDEX
    Explanations

    mathematical/programmatic expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     privé
    -0.07
     условиях
    -0.07
    ringe
    -0.07
    給
    -0.07
    oriously
    -0.07
    /min
    -0.07
    �
    -0.07
    百亿
    -0.06
    /org
    -0.06
    给
    -0.06
    POSITIVE LOGITS
    _helper
    0.07
    Roles
    0.07
     college
    0.07
    Петербур
    0.07
     serão
    0.07
     Metal
    0.07
    ohan
    0.07
     Enhancement
    0.07
    𬳿
    0.07
    חליף
    0.07
    Act Density 0.013%

    No Known Activations