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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     حض
    -0.06
     خلال
    -0.06
     зас
    -0.06
     govern
    -0.06
     "");
    -0.06
    iance
    -0.06
     soluble
    -0.06
     "><
    -0.06
    invitation
    -0.06
    POSITIVE LOGITS
    ают
    0.07
    ¦
    0.07
     costume
    0.07
    guards
    0.07
     Lena
    0.06
    margin
    0.06
    ивают
    0.06
     اک
    0.06
    -font
    0.06
     Currency
    0.06
    Act Density 0.033%

    No Known Activations