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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Perform
    -0.07
    ordo
    -0.07
    aje
    -0.07
    erville
    -0.07
     aiding
    -0.06
     сред
    -0.06
     divorce
    -0.06
     respected
    -0.06
     dejtingsaj
    -0.06
     tahun
    -0.06
    POSITIVE LOGITS
    />\
    0.07
    νοια
    0.06
    .Usage
    0.06
    誤
    0.06
    KW
    0.06
     Accountability
    0.06
    .parametrize
    0.06
    ूबर
    0.06
    FullScreen
    0.06
    .uml
    0.06
    Act Density 0.004%

    No Known Activations