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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     मेरो
    -0.08
    တွက်
    -0.08
     qor
    -0.08
    ောင်း
    -0.07
     juba
    -0.07
     မ
    -0.07
     tayari
    -0.07
     stor
    -0.07
     kisi
    -0.07
     SSA
    -0.07
    POSITIVE LOGITS
     الحوار
    0.09
     terwijl
    0.09
     backstage
    0.08
     возле
    0.08
     während
    0.08
     Telephone
    0.08
    _ESC
    0.08
    (names
    0.08
     během
    0.08
     antics
    0.08
    Act Density 0.084%

    No Known Activations