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

    Neuronpedia

    INDEX
    Explanations

    step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caves
    0.75
     kumb
    0.73
    賁
    0.73
     Explosion
    0.73
    গোল
    0.71
     knives
    0.71
     RetValue
    0.70
     pral
    0.69
     Saltar
    0.68
     allies
    0.68
    POSITIVE LOGITS
    
    0.74
    ๆ
    0.70
    ­
    0.69
    ៗ
    0.68
    மிருந்து
    0.64
    ؍
    0.64
    संर
    0.63
     सिरे
    0.63
    ("");
    0.62
    рано
    0.61
    Act Density 0.041%

    No Known Activations