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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atron
    -0.07
     Theme
    -0.07
     qu
    -0.06
    aset
    -0.06
    CU
    -0.06
     &&↵
    -0.06
    όρ
    -0.06
    ack
    -0.06
    ży
    -0.06
    abilmek
    -0.06
    POSITIVE LOGITS
     updateUser
    0.07
    .FAIL
    0.07
    なかった
    0.07
    ustainability
    0.06
     FileInputStream
    0.06
    .Fatal
    0.06
     removeObject
    0.06
    -good
    0.06
    aversable
    0.06
     refunded
    0.06
    Act Density 0.159%

    No Known Activations