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

    Neuronpedia

    INDEX
    Explanations

    code generation of model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Genero
    0.42
    ま
    0.41
    word
    0.40
    Glen
    0.39
    ㎝
    0.38
    னுடன்
    0.37
    obedience
    0.36
    จัดการ
    0.36
    Wr
    0.36
    rau
    0.36
    POSITIVE LOGITS
     RIA
    0.41
     кода
    0.41
     метров
    0.39
    mainWindow
    0.39
     kodu
    0.38
    ಿಕ್
    0.37
     enlargement
    0.36
     Examining
    0.36
    CreateModel
    0.36
    CHUNK
    0.36
    Act Density 0.029%

    No Known Activations