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

    Neuronpedia

    INDEX
    Explanations

    box itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bullet
    0.59
     Red
    0.57
     employed
    0.56
    省略
    0.54
     използва
    0.54
     Young
    0.54
    P
    0.54
    D
    0.53
     German
    0.53
    L
    0.53
    POSITIVE LOGITS
     itself
    0.87
    ၏
    0.84
     نفسها
    0.80
    .\"
    0.77
     failings
    0.77
    ."'
    0.77
     ayatan
    0.75
    !")
    0.75
     fondly
    0.74
    .""
    0.74
    Act Density 0.618%

    No Known Activations