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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    腯
    -0.07
    .Assign
    -0.07
    唣
    -0.07
    getApplication
    -0.07
     unserialize
    -0.06
     PLAY
    -0.06
    .package
    -0.06
     edu
    -0.06
    /Foundation
    -0.06
    _slave
    -0.06
    POSITIVE LOGITS
     parallels
    0.08
    icing
    0.08
    ню
    0.07
    _duplicates
    0.07
    -drop
    0.07
     paths
    0.07
     questões
    0.07
     groove
    0.07
    调侃
    0.07
     sizing
    0.07
    Act Density 0.046%

    No Known Activations