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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     burnt
    -0.07
     Above
    -0.07
     CPL
    -0.07
    radu
    -0.06
    ESS
    -0.06
    WK
    -0.06
     пу
    -0.06
    olet
    -0.06
    ρών
    -0.06
    又
    -0.06
    POSITIVE LOGITS
     mortgage
    0.07
     Heidi
    0.07
    985
    0.07
     Αλ
    0.07
     ukaz
    0.07
     Ide
    0.06
    id
    0.06
     werde
    0.06
     transmissions
    0.06
    webdriver
    0.06
    Act Density 0.000%

    No Known Activations