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

    Neuronpedia

    INDEX
    Explanations

    Questions and edge cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    that
    -0.08
     اع
    -0.07
    Ql
    -0.07
     সাক্ষ
    -0.07
    れ
    -0.07
     beautiful
    -0.07
     соверш
    -0.07
     waarin
    -0.07
    তম
    -0.07
     DOE
    -0.07
    POSITIVE LOGITS
     Undefined
    0.10
    .Allow
    0.09
     habría
    0.09
    Undefined
    0.09
     laha
    0.08
    .Disabled
    0.08
    (Border
    0.08
     dianggap
    0.08
    ibição
    0.08
     Frankreich
    0.08
    Act Density 0.044%

    No Known Activations