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

    Neuronpedia

    INDEX
    Explanations

    organic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    吃到
    -0.07
    불
    -0.07
    charge
    -0.07
    (Command
    -0.07
    总有
    -0.06
    扺
    -0.06
    poser
    -0.06
    ateg
    -0.06
     dismiss
    -0.06
    POSITIVE LOGITS
     Forest
    0.07
    atica
    0.07
    .ReadUInt
    0.07
     против
    0.07
     Hannity
    0.07
     Serialization
    0.07
    .pk
    0.07
    _binary
    0.06
    🐟
    0.06
    .Focus
    0.06
    Act Density 0.005%

    No Known Activations