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

    Neuronpedia

    INDEX
    Explanations

    company descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auce
    -0.08
    하시
    -0.07
     ilan
    -0.07
    bane
    -0.06
    카
    -0.06
     Barack
    -0.06
    .literal
    -0.06
     біблі
    -0.06
    �
    -0.06
     pains
    -0.06
    POSITIVE LOGITS
     functional
    0.06
     유형
    0.06
    .exe
    0.06
    .Rad
    0.06
    DK
    0.06
     Cover
    0.06
     Much
    0.05
    ward
    0.05
     SF
    0.05
    getStore
    0.05
    Act Density 0.057%

    No Known Activations