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

    Neuronpedia

    INDEX
    Explanations

    introducing options or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     జరుగు
    0.51
    **
    0.51
     AKA
    0.50
    pip
    0.49
    عادة
    0.49
    вот
    0.49
     আকারে
    0.49
    略
    0.47
    ంటర్
    0.47
    **/
    0.47
    POSITIVE LOGITS
     protect
    0.82
     medit
    0.82
     karn
    0.80
     hazards
    0.80
     man
    0.78
     bescherm
    0.78
     invest
    0.78
     bebe
    0.78
     dekor
    0.78
     portug
    0.77
    Act Density 0.077%

    No Known Activations