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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =============↵
    -0.07
     ADA
    -0.06
     �
    -0.06
     glyphs
    -0.06
     lazy
    -0.06
     breakfast
    -0.06
    insn
    -0.06
     strained
    -0.06
    logen
    -0.06
     contentView
    -0.06
    POSITIVE LOGITS
    vit
    0.07
    erdale
    0.06
     зберіг
    0.06
    terror
    0.06
     Kyoto
    0.06
    様
    0.06
     Wear
    0.06
    ACLE
    0.06
     hypers
    0.06
    -paying
    0.06
    Act Density 0.000%

    No Known Activations