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

    Neuronpedia

    INDEX
    Explanations

    they often have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ENTER
    0.66
    ármaz
    0.63
    endDate
    0.62
    ﾇ
    0.62
    過ご
    0.61
    צל
    0.61
    enjoy
    0.60
     воспомина
    0.60
    InitStruct
    0.60
    spent
    0.59
    POSITIVE LOGITS
     you
    0.77
     systems
    0.71
     *
    0.69
     website
    0.66
     prohibits
    0.66
     ofrecen
    0.66
     offers
    0.65
     rainforest
    0.65
     coasters
    0.64
     allows
    0.64
    Act Density 0.029%

    No Known Activations