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

    Neuronpedia

    INDEX
    Explanations

    of/the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assembling
    -0.07
     weekend
    -0.06
    Playable
    -0.06
    _chain
    -0.06
    드로
    -0.06
     deportation
    -0.06
     },{↵
    -0.06
     renewed
    -0.06
    决
    -0.06
    δες
    -0.06
    POSITIVE LOGITS
     kennenlernen
    0.06
    siblings
    0.06
    Ren
    0.06
     M
    0.06
     Para
    0.06
    -effect
    0.06
     PE
    0.06
     entender
    0.06
     AHL
    0.06
     alış
    0.06
    Act Density 0.073%

    No Known Activations