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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kInstruction
    -0.07
    .gdx
    -0.06
     legisl
    -0.06
     persists
    -0.06
    -common
    -0.06
    (pwd
    -0.06
    .Image
    -0.06
    Admin
    -0.06
     Madonna
    -0.06
    ifle
    -0.06
    POSITIVE LOGITS
    employer
    0.07
    	date
    0.07
     Was
    0.07
    ).'</
    0.07
     civilian
    0.06
     tỉ
    0.06
     Sand
    0.06
    씨
    0.06
     Alan
    0.06
     언제
    0.06
    Act Density 0.017%

    No Known Activations