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

    Neuronpedia

    INDEX
    Explanations

    variable types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нах
    -0.06
    �다
    -0.06
     zwe
    -0.06
     Fuller
    -0.06
     Ly
    -0.06
     milli
    -0.06
    (Render
    -0.06
    玄
    -0.06
     Relationship
    -0.06
     ار
    -0.06
    POSITIVE LOGITS
     forbidden
    0.07
     navigationOptions
    0.07
     والح
    0.07
    emain
    0.07
     okum
    0.07
    coords
    0.07
     vibration
    0.07
    농
    0.06
    Containing
    0.06
     succession
    0.06
    Act Density 0.014%

    No Known Activations