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

    Neuronpedia

    INDEX
    Explanations

    special characters and `Function`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     которому
    0.47
     Sabemos
    0.46
    getCharAt
    0.44
    などを
    0.44
    🙏🙏
    0.44
    ?</
    0.43
     নারায়ণ
    0.43
    ២
    0.42
     twentieth
    0.41
     errores
    0.41
    POSITIVE LOGITS
    다
    0.45
    า
    0.44
    ంశ
    0.41
    I
    0.41
    िक
    0.41
     предназначен
    0.41
    𝘼
    0.41
    ikko
    0.40
    ühl
    0.40
     институт
    0.40
    Act Density 0.022%

    No Known Activations