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

    Neuronpedia

    INDEX
    Explanations

    improve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tick
    -0.07
    uz
    -0.07
     beberapa
    -0.06
    Ide
    -0.06
    _nr
    -0.06
     tengo
    -0.06
     erected
    -0.06
    フレ
    -0.06
    пе
    -0.06
    UZ
    -0.05
    POSITIVE LOGITS
     //$
    0.07
     Fathers
    0.07
     PHYS
    0.07
    malıdır
    0.07
    ियर
    0.06
    บค
    0.06
     franç
    0.06
    /providers
    0.06
    imen
    0.06
    Angular
    0.06
    Act Density 0.024%

    No Known Activations