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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     návr
    -0.07
     пти
    -0.07
     блю
    -0.06
    lates
    -0.06
    (Yii
    -0.06
     LAND
    -0.06
    .bind
    -0.06
     Kore
    -0.06
     encoding
    -0.06
     những
    -0.06
    POSITIVE LOGITS
    hashed
    0.07
     FullName
    0.06
     ç
    0.06
    xFFFFFFFF
    0.06
     homosexuality
    0.06
     transitioning
    0.06
     Brazil
    0.06
     UV
    0.06
    DropDown
    0.06
    venge
    0.06
    Act Density 0.033%

    No Known Activations