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

    Neuronpedia

    INDEX
    Explanations

    inequalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    berto
    -0.09
     einfache
    -0.08
    ರ್ಚ
    -0.08
    .find
    -0.08
    ಗ್ಗ
    -0.08
    (Simple
    -0.08
    wara
    -0.08
     bestem
    -0.08
    -building
    -0.08
    (find
    -0.07
    POSITIVE LOGITS
     excludes
    0.11
     estrict
    0.09
     prohibits
    0.09
    exclude
    0.09
     misses
    0.09
     inklud
    0.09
     slightest
    0.09
     includes
    0.09
     uključ
    0.08
     includ
    0.08
    Act Density 0.056%

    No Known Activations