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

    Neuronpedia

    INDEX
    Explanations

    scale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coffee
    -0.07
    _photos
    -0.07
     choices
    -0.06
    _constructor
    -0.06
     welcoming
    -0.06
    blood
    -0.06
    或許
    -0.06
    跑步
    -0.06
     dinners
    -0.06
    冰箱
    -0.06
    POSITIVE LOGITS
    .TRA
    0.09
     Activity
    0.08
    酆
    0.07
    廒
    0.07
     oxidation
    0.07
     AssemblyTitle
    0.07
    (ByVal
    0.07
    _TIMESTAMP
    0.07
    技法
    0.07
    两
    0.07
    Act Density 0.007%

    No Known Activations