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

    Neuronpedia

    INDEX
    Explanations

    preventing or avoiding

    np_acts-logits-general · gemini-2.5-flash-lite

    avoid dictionary words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.82
     imbued
    0.75
    ‌ها
    0.66
     היו
    0.66
    ”،
    0.66
     “,
    0.66
    ᐟ
    0.65
    br
    0.64
    grande
    0.64
     ovation
    0.64
    POSITIVE LOGITS
    防止
    0.79
    .
    0.75
    避免
    0.74
    ו
    0.74
    of
    0.68
    ак
    0.64
    at
    0.63
     voorkomen
    0.63
    வ்வாறு
    0.62
    瞌
    0.62
    Act Density 0.752%

    No Known Activations