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

    Neuronpedia

    INDEX
    Explanations

    model scenario

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Equation
    -0.08
     levels
    -0.08
    Pad
    -0.08
     pad
    -0.08
     Pads
    -0.07
    Pads
    -0.07
    킬
    -0.07
    obet
    -0.07
     Equation
    -0.07
    Nap
    -0.07
    POSITIVE LOGITS
     plausible
    0.10
     تصور
    0.10
     conceivable
    0.09
     imagined
    0.09
     scenario
    0.09
     concret
    0.08
     Scenario
    0.08
     scénario
    0.08
     hypothetical
    0.08
     imagining
    0.08
    Act Density 0.039%

    No Known Activations