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

    Neuronpedia

    INDEX
    Explanations

    powers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilmektedir
    -0.06
     McCartney
    -0.06
    ційна
    -0.06
     mainland
    -0.06
     Nero
    -0.06
     awe
    -0.06
     GNUNET
    -0.06
     Kanun
    -0.06
    阪
    -0.06
     boys
    -0.06
    POSITIVE LOGITS
    .Hidden
    0.08
    USR
    0.07
    (meta
    0.07
    _beg
    0.07
     criticizing
    0.07
    thought
    0.06
     Harness
    0.06
    uint
    0.06
    curl
    0.06
    .GetText
    0.06
    Act Density 0.000%

    No Known Activations