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

    Neuronpedia

    INDEX
    Explanations

    notes and clarifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fungi
    -0.09
    بدو
    -0.08
     impreg
    -0.08
     होती
    -0.08
    sync
    -0.08
     હતો
    -0.08
    Sous
    -0.08
    <Http
    -0.08
    شب
    -0.08
     చెందిన
    -0.07
    POSITIVE LOGITS
     Assume
    0.09
     Please
    0.08
    ashing
    0.08
     Note
    0.08
     Determine
    0.08
     注意
    0.08
     Moral
    0.08
     Definitions
    0.07
     Ensure
    0.07
     Care
    0.07
    Act Density 0.025%

    No Known Activations