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

    Neuronpedia

    INDEX
    Explanations

    statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kilometers
    -0.08
     interns
    -0.07
     masters
    -0.06
     percent
    -0.06
    -interest
    -0.06
    раг
    -0.06
     Photo
    -0.06
    MESS
    -0.06
     incremental
    -0.06
    .fetchall
    -0.06
    POSITIVE LOGITS
    ++++++++++++++++
    0.07
    volution
    0.06
    ≧
    0.06
    JSImport
    0.06
     rapp
    0.06
    ілля
    0.06
     hotelu
    0.06
    ')
↵
↵
    0.06
    ök
    0.06
    -highlight
    0.06
    Act Density 0.031%

    No Known Activations