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

    Neuronpedia

    INDEX
    Explanations

    save and run code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ";
    0.64
     iniziale
    0.61
    ;
    0.59
     السابقه
    0.58
     (“
    0.57
     })
    0.57
     )[
    0.56
     ("
    0.55
     "";
    0.55
     ])
    0.54
    POSITIVE LOGITS
     blaming
    0.59
     affirmation
    0.58
     affirm
    0.57
    মহাদেশ
    0.56
     affirming
    0.56
    ಿಗಳು
    0.56
    revalidator
    0.55
    ActionMode
    0.55
    이너
    0.55
     Affirm
    0.55
    Act Density 0.031%

    No Known Activations