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

    Neuronpedia

    INDEX
    Explanations

    Cheetahs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Progress
    -0.07
    =Value
    -0.07
    Initialized
    -0.07
    define
    -0.07
     »
    -0.06
    些什么
    -0.06
     Price
    -0.06
    (progress
    -0.06
    录制
    -0.06
    鹪
    -0.06
    POSITIVE LOGITS
     bead
    0.07
    药师
    0.07
     teachers
    0.07
    وج
    0.07
    .timing
    0.07
    ibi
    0.07
     taco
    0.07
    obia
    0.07
    中毒
    0.06
    感染者
    0.06
    Act Density 0.001%

    No Known Activations