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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺮ
    -0.06
    �이
    -0.06
     f
    -0.06
    into
    -0.06
    .getModel
    -0.06
    opis
    -0.06
    flush
    -0.06
    !</
    -0.05
     tooth
    -0.05
     принимать
    -0.05
    POSITIVE LOGITS
     assignable
    0.07
    าก
    0.07
    ANNOT
    0.07
    ARP
    0.07
     poder
    0.07
     souvent
    0.07
    tems
    0.06
    ención
    0.06
     stati
    0.06
     lesser
    0.06
    Act Density 0.000%

    No Known Activations