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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quir
    -0.07
    Constructed
    -0.06
     HTTP
    -0.06
     lug
    -0.06
    :{↵
    -0.06
     später
    -0.06
    Ideal
    -0.06
     Vall
    -0.06
     callbacks
    -0.06
     ult
    -0.06
    POSITIVE LOGITS
     allies
    0.06
     приступ
    0.06
    常
    0.06
    DV
    0.06
    edis
    0.06
    ồ
    0.06
    هه
    0.06
     suspense
    0.06
    (argument
    0.06
     приб
    0.05
    Act Density 0.144%

    No Known Activations