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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plainly
    -0.07
     misses
    -0.06
     onCancel
    -0.06
    Stroke
    -0.06
    Resolve
    -0.06
     cancel
    -0.06
    mare
    -0.06
    rance
    -0.06
     nervous
    -0.06
     Gandhi
    -0.06
    POSITIVE LOGITS
    *)&
    0.07
    parameter
    0.06
    익
    0.06
    教训
    0.06
     Markets
    0.06
     culturally
    0.06
    الية
    0.06
     respecting
    0.06
     generating
    0.06
    Φ
    0.06
    Act Density 0.003%

    No Known Activations