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

    Neuronpedia

    INDEX
    Explanations

    <|start|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tempor
    -0.08
     extensions
    -0.08
     tilt
    -0.08
     unn
    -0.07
     zeit
    -0.07
    -0.07
     surplus
    -0.07
     tarifas
    -0.07
     Fundament
    -0.07
    (({
    -0.07
    POSITIVE LOGITS
    On
    0.08
    Synopsis
    0.07
    RT
    0.07
     ي
    0.07
     хотите
    0.07
    "↵↵
    0.07
    _RT
    0.07
    ↵↵↵
    0.07
    ↵↵
    0.07
    ă
    0.07
    Act Density 0.024%
    No Known Activations