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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MAP
    -0.07
    ialized
    -0.07
     id
    -0.06
    "No
    -0.06
    eker
    -0.06
     vault
    -0.06
    authorized
    -0.06
    chant
    -0.06
     movers
    -0.06
    湾
    -0.06
    POSITIVE LOGITS
     adequately
    0.07
     úspě
    0.06
     dejar
    0.06
     Jun
    0.06
     Campus
    0.06
     Product
    0.06
     JAN
    0.06
     dude
    0.06
    JSGlobalScope
    0.06
    اسب
    0.06
    Act Density 0.042%

    No Known Activations