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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    笼罩
    -0.08
    킁
    -0.07
     Jean
    -0.07
     Ross
    -0.07
     Coll
    -0.07
     Nad
    -0.07
     Ich
    -0.07
    rypted
    -0.06
    Mil
    -0.06
    ilateral
    -0.06
    POSITIVE LOGITS
     favors
    0.07
    .baseUrl
    0.07
    ㄚ
    0.07
    .firebase
    0.06
    .Abs
    0.06
    萏
    0.06
    ⫸
    0.06
     wholes
    0.06
    '];
    0.06
    ᵔ
    0.06
    Act Density 0.002%

    No Known Activations