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

    Neuronpedia

    INDEX
    Explanations

    greetings and salutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Exemple
    0.43
    叄
    0.42
    ,"@
    0.41
     Anyways
    0.40
     Editar
    0.39
     formulae
    0.39
     พิจิก
    0.39
    crits
    0.38
     );//
    0.38
     দেখুনঃ
    0.38
    POSITIVE LOGITS
     Hello
    0.90
    Hello
    0.84
     hello
    0.81
    hello
    0.69
    Greetings
    0.66
     हेलो
    0.60
    Hi
    0.57
    안녕하세요
    0.57
     Greetings
    0.57
     Hallo
    0.56
    Act Density 0.000%

    No Known Activations