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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flowers
    -0.07
     Task
    -0.07
    とき
    -0.07
    	string
    -0.07
     traveled
    -0.06
    oir
    -0.06
     scraped
    -0.06
     LY
    -0.06
    LY
    -0.06
     Exactly
    -0.06
    POSITIVE LOGITS
    在线视频
    0.07
    _uv
    0.07
     creampie
    0.07
     بعض
    0.07
    лач
    0.07
    =new
    0.07
    ，最
    0.06
    =default
    0.06
    Abb
    0.06
    Verbose
    0.06
    Act Density 0.080%

    No Known Activations