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

    Neuronpedia

    INDEX
    Explanations

    sell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     percentages
    -0.09
    Percentage
    -0.09
    percentage
    -0.08
     Percentage
    -0.08
     statistical
    -0.08
     പ്രവ
    -0.08
     percentage
    -0.08
     commercial
    -0.08
     sinful
    -0.08
    typescript
    -0.08
    POSITIVE LOGITS
     хут
    0.08
    .ge
    0.08
     meetup
    0.08
     mande
    0.08
    .norm
    0.07
    .he
    0.07
     agencias
    0.07
     ramo
    0.07
    (render
    0.07
    ’ya
    0.07
    Act Density 0.017%

    No Known Activations