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

    Neuronpedia

    INDEX
    Explanations

    Errors and debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ng
    -0.07
    CID
    -0.07
     Validates
    -0.07
    vid
    -0.07
    timer
    -0.06
     =================================
    -0.06
    一名
    -0.06
    #######↵
    -0.06
    	max
    -0.06
     clinically
    -0.06
    POSITIVE LOGITS
     principio
    0.08
    subnet
    0.08
     Force
    0.07
    色情
    0.07
    昇
    0.07
    ˁ
    0.07
    щит
    0.07
     le
    0.07
    干涉
    0.07
    ialect
    0.07
    Act Density 0.024%

    No Known Activations