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

    Neuronpedia

    INDEX
    Explanations

    a breakdown of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aficionados
    0.54
     encased
    0.52
     iteratively
    0.51
     atomically
    0.47
     آمد
    0.47
     embeddings
    0.47
     algorithms
    0.46
     Intro
    0.46
     accents
    0.46
     automata
    0.46
    POSITIVE LOGITS
     lot
    0.80
     variety
    0.74
     whopping
    0.69
     multitude
    0.69
     veritable
    0.69
    <unused2126>
    0.67
     number
    0.65
     bunch
    0.65
     plethora
    0.64
    <unused2172>
    0.59
    Act Density 0.928%

    No Known Activations