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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spot
    -0.07
    ียวก
    -0.06
    MSC
    -0.06
    head
    -0.06
    �
    -0.06
    QUEST
    -0.06
    ็น
    -0.06
     Ish
    -0.06
    ortal
    -0.06
     vanish
    -0.06
    POSITIVE LOGITS
    λι
    0.07
    485
    0.06
    underscore
    0.06
     "#"
    0.06
    UserProfile
    0.06
    _continue
    0.06
    우
    0.06
     بحث
    0.06
     �
    0.06
    hesive
    0.06
    Act Density 0.000%

    No Known Activations