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

    Neuronpedia

    INDEX
    Explanations

    computer commands and jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    financial
    -0.07
    �
    -0.07
    атків
    -0.07
    農
    -0.07
    .regex
    -0.06
    iram
    -0.06
     vegetables
    -0.06
    恩
    -0.06
    ạch
    -0.06
    CHANGE
    -0.06
    POSITIVE LOGITS
     Wake
    0.06
     Workspace
    0.06
     recept
    0.06
     unified
    0.06
     unify
    0.06
     Seks
    0.06
    Eth
    0.06
    -led
    0.06
     Side
    0.06
    Pet
    0.06
    Act Density 0.015%

    No Known Activations