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

    Neuronpedia

    INDEX
    Explanations

    ä

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Сов
    -0.06
    '>$
    -0.06
     Ко
    -0.06
    pow
    -0.06
     devis
    -0.06
     แต
    -0.06
    official
    -0.06
     SWAT
    -0.06
     उसस
    -0.06
    ereço
    -0.06
    POSITIVE LOGITS
    ンズ
    0.07
    ίν
    0.07
     Lý
    0.07
    ingers
    0.06
    omens
    0.06
    SENS
    0.06
    Bindings
    0.06
    onders
    0.06
     APPLICATION
    0.06
    藥
    0.06
    Act Density 0.000%

    No Known Activations