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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pubkey
    -0.08
    世上
    -0.07
     Carson
    -0.07
    anza
    -0.07
     JM
    -0.07
    穴位
    -0.07
     함께
    -0.07
    “
    -0.07
     TOO
    -0.07
    (chip
    -0.07
    POSITIVE LOGITS
    ive
    0.07
    ։
    0.07
    ﾜ
    0.07
    Fine
    0.07
     Dining
    0.07
    嚴
    0.06
    年の
    0.06
    delegate
    0.06
    енных
    0.06
    LIB
    0.06
    Act Density 0.022%

    No Known Activations