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

    Neuronpedia

    INDEX
    Explanations

    elements hydrogen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sentence
    0.45
    ,
    0.42
     Sorrow
    0.42
     equated
    0.41
     sentences
    0.41
    etaan
    0.41
    珴
    0.41
     regret
    0.40
     reacting
    0.40
     underscored
    0.40
    POSITIVE LOGITS
    vidia
    0.49
     ingeniería
    0.41
     firmy
    0.41
    кут
    0.40
     প্রয
    0.39
     ജില്ലാ
    0.39
    PROJECT
    0.39
     можа
    0.39
     ibang
    0.39
     mighty
    0.39
    Act Density 0.354%

    No Known Activations