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

    Neuronpedia

    INDEX
    Explanations

    ]]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    measure
    -0.08
     Cause
    -0.07
    _VE
    -0.07
     не
    -0.07
     requestCode
    -0.07
    -body
    -0.07
    [group
    -0.07
     Height
    -0.07
    ocations
    -0.07
    .estado
    -0.07
    POSITIVE LOGITS
    сп
    0.07
    렵
    0.06
     loan
    0.06
    系统
    0.06
    য
    0.06
     pard
    0.06
     IRS
    0.06
     עבודות
    0.06
    faces
    0.06
    ﻃ
    0.06
    Act Density 0.001%

    No Known Activations