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

    Neuronpedia

    INDEX
    Explanations

    time span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dark
    -0.06
     charges
    -0.06
    ierte
    -0.06
     lawn
    -0.06
     insightful
    -0.06
    Same
    -0.06
     Almost
    -0.06
    _break
    -0.06
    _square
    -0.06
    awn
    -0.06
    POSITIVE LOGITS
    „N
    0.07
     asoci
    0.07
     Regel
    0.07
    pillar
    0.06
     Usually
    0.06
    quake
    0.06
     displ
    0.06
    .Priority
    0.06
    ved
    0.06
    iculos
    0.06
    Act Density 0.020%

    No Known Activations