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

    Neuronpedia

    INDEX
    Explanations

    using analogies for explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ického
    0.89
     irgendwie
    0.86
     quasi
    0.85
    についての
    0.77
    
    0.76
     either
    0.76
     voire
    0.75
    olytic
    0.74
    whatever
    0.74
    াবির
    0.73
    POSITIVE LOGITS
    Many
    0.72
     stos
    0.72
    When
    0.68
     हिमालय
    0.65
     many
    0.64
    it
    0.64
     Hundreds
    0.62
     teams
    0.62
     personer
    0.61
     hundreds
    0.61
    Act Density 0.093%

    No Known Activations