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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Any
    -0.07
     Beats
    -0.07
     broadcaster
    -0.07
     Continuous
    -0.06
    Warm
    -0.06
    _any
    -0.06
     pressing
    -0.06
    ände
    -0.06
    112
    -0.06
     값을
    -0.06
    POSITIVE LOGITS
     overlap
    0.06
    DialogContent
    0.06
    /gl
    0.06
    esome
    0.06
     hopeless
    0.06
    оп
    0.06
    .threshold
    0.06
     sidebar
    0.06
    اتر
    0.06
    /items
    0.05
    Act Density 0.254%

    No Known Activations