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

    Neuronpedia

    INDEX
    Explanations

    that the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vpn
    -0.07
     racer
    -0.07
    lista
    -0.07
    .Matcher
    -0.06
     imped
    -0.06
    population
    -0.06
    ستم
    -0.06
    brities
    -0.06
    iente
    -0.06
    ollections
    -0.06
    POSITIVE LOGITS
    Spr
    0.07
    ']↵
    0.07
    @"↵
    0.07
    zeň
    0.07
     fodder
    0.06
     Gather
    0.06
     sono
    0.06
     ziyaret
    0.06
     arsen
    0.06
    (mContext
    0.06
    Act Density 0.011%

    No Known Activations