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

    Neuronpedia

    INDEX
    Explanations

    positive progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conveyor
    -0.08
     Worker
    -0.06
    encrypt
    -0.06
    Сам
    -0.06
    Zero
    -0.06
     kad
    -0.06
    <Key
    -0.06
    <Text
    -0.06
     helium
    -0.06
    UserData
    -0.06
    POSITIVE LOGITS
     cb
    0.07
    명의
    0.07
    youtube
    0.06
     dlg
    0.06
    .physics
    0.06
    ानव
    0.06
     ofrece
    0.06
     fencing
    0.06
     onDataChange
    0.06
     많은
    0.06
    Act Density 0.080%

    No Known Activations