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

    Neuronpedia

    INDEX
    Explanations

    code models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Expedia
    0.75
    （
    0.69
     iterations
    0.66
    IKA
    0.64
     increments
    0.64
     Palmas
    0.64
     Astros
    0.63
     Libraries
    0.63
     theatres
    0.63
     விமானங்கள்
    0.62
    POSITIVE LOGITS
     chamado
    0.68
    specific
    0.67
    )$.
    0.64
    URE
    0.61
    );
    0.59
    !);
    0.59
    man
    0.57
     don
    0.57
     as
    0.57
     الب
    0.57
    Act Density 0.002%

    No Known Activations