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

    Neuronpedia

    INDEX
    Explanations

    customer reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slam
    -0.07
     安
    -0.07
     bitcoins
    -0.07
     cautious
    -0.07
     існу
    -0.06
     perspective
    -0.06
     TIMEOUT
    -0.06
    clicked
    -0.06
     PSP
    -0.06
    ████
    -0.06
    POSITIVE LOGITS
     behand
    0.06
    เศ
    0.06
     отмеч
    0.06
     требует
    0.06
    statuses
    0.06
     maneu
    0.06
     بنی
    0.06
     acos
    0.06
     melted
    0.05
    Eth
    0.05
    Act Density 0.022%

    No Known Activations