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

    Neuronpedia

    INDEX
    Explanations

    inter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     increments
    -0.06
    'eau
    -0.06
     внутрен
    -0.06
    abar
    -0.06
    ål
    -0.06
     прох
    -0.06
    ;j
    -0.05
     Trees
    -0.05
     stalled
    -0.05
     спри
    -0.05
    POSITIVE LOGITS
    sar
    0.07
     {{
    0.07
     म
    0.07
     MS
    0.07
    ALLERY
    0.07
     assemblies
    0.07
     asbestos
    0.06
     個
    0.06
    tight
    0.06
     coherent
    0.06
    Act Density 0.006%

    No Known Activations