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

    Neuronpedia

    INDEX
    Explanations

    code block language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒆜
    0.43
    지컬
    0.43
    혐
    0.41
    ConfigRequest
    0.41
    အနေ
    0.40
    ">+
    0.40
    thisobject
    0.40
    Facilities
    0.39
     युवकों
    0.39
    잖아요
    0.39
    POSITIVE LOGITS
     ```
    0.39
     pdf
    0.38
    roma
    0.37
    ⭐⭐
    0.35
     medicine
    0.35
     Step
    0.35
     lưu
    0.34
     ''.
    0.33
    medicine
    0.33
     step
    0.33
    Act Density 0.001%

    No Known Activations