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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contexts
    -0.06
     btn
    -0.06
    .ContextCompat
    -0.06
    moment
    -0.06
    _eff
    -0.06
     wf
    -0.06
     coached
    -0.06
     manslaughter
    -0.06
     rej
    -0.06
    System
    -0.06
    POSITIVE LOGITS
     phát
    0.07
     pleading
    0.07
    .addObject
    0.07
     siding
    0.06
     Trab
    0.06
     konce
    0.06
     соч
    0.06
    قد
    0.06
    Bounds
    0.06
     Báo
    0.06
    Act Density 0.060%

    No Known Activations