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

    Neuronpedia

    INDEX
    Explanations

    essay introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     list
    0.63
    简单的
    0.54
    簡單
    0.52
     varios
    0.50
     simple
    0.49
     mấy
    0.49
     info
    0.49
     paio
    0.49
     informação
    0.48
     simples
    0.47
    POSITIVE LOGITS
     explores
    0.51
    Firstly
    0.50
     Firstly
    0.49
     Below
    0.48
    follows
    0.47
     below
    0.47
     delves
    0.47
    below
    0.46
    首先
    0.46
    Below
    0.45
    Act Density 0.004%

    No Known Activations