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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peč
    -0.07
    erse
    -0.06
     souvent
    -0.06
    PIO
    -0.06
     rigor
    -0.06
    Geometry
    -0.06
     enduring
    -0.06
    εί
    -0.06
    okers
    -0.06
    Если
    -0.06
    POSITIVE LOGITS
     informing
    0.07
     waveform
    0.07
     Goku
    0.07
     Sampling
    0.07
     Monitor
    0.06
    amide
    0.06
     cms
    0.06
     ridicule
    0.06
     Fundamental
    0.06
    _reg
    0.06
    Act Density 0.012%

    No Known Activations