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

    Neuronpedia

    INDEX
    Explanations

    Diminutives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    转载
    -0.08
    .Raycast
    -0.08
     aline
    -0.08
    println
    -0.08
     empêcher
    -0.08
     persen
    -0.08
     wer
    -0.07
     impedir
    -0.07
    ект
    -0.07
     actualizar
    -0.07
    POSITIVE LOGITS
     affectionate
    0.09
    cute
    0.09
     affection
    0.09
     respectfully
    0.09
     친
    0.09
     cute
    0.08
     الكبير
    0.08
     کوچک
    0.08
     GRAN
    0.08
     adorable
    0.08
    Act Density 0.008%

    No Known Activations