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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -aged
    -0.07
     Kenn
    -0.06
     independent
    -0.06
    Browsable
    -0.06
    -Day
    -0.06
    ारक
    -0.06
    .Logging
    -0.06
    _uv
    -0.06
     André
    -0.06
    PIPE
    -0.06
    POSITIVE LOGITS
     보고
    0.07
    person
    0.06
     onPress
    0.06
     touted
    0.06
    (common
    0.06
     enfrent
    0.06
    0.06
     ihtiyac
    0.06
    VAL
    0.06
    지고
    0.06
    Act Density 0.008%

    No Known Activations