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

    Neuronpedia

    INDEX
    Explanations

    improves performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     njemu
    0.41
    eduanya
    0.40
     hacerlo
    0.39
    fireFlower
    0.39
     దాని
    0.38
    getType
    0.38
    ujjati
    0.38
     tumeur
    0.38
     उक्त
    0.37
    遶
    0.37
    POSITIVE LOGITS
    :
    0.44
    ,
    0.44
     in
    0.38
     effortlessly
    0.38
     routinely
    0.37
    越来越多
    0.36
     जेव्हा
    0.36
    ↵
    0.36
     collectively
    0.35
    .
    0.34
    Act Density 0.240%

    No Known Activations