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

    Neuronpedia

    INDEX
    Explanations

    toothpaste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adding
    0.64
    IF
    0.57
    kontrol
    0.57
    ח
    0.57
    اب
    0.56
    defined
    0.54
    determining
    0.54
    telefono
    0.54
    aint
    0.53
     definisi
    0.53
    POSITIVE LOGITS
    ї
    0.62
     toothbrush
    0.61
     toothpaste
    0.58
     Jinping
    0.56
     Você
    0.55
    𝐕
    0.54
     brushing
    0.54
    }";
    0.53
     Rosh
    0.53
     Premier
    0.53
    Act Density 0.003%

    No Known Activations