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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infographic
    -0.07
    estion
    -0.07
    Runtime
    -0.07
     آس
    -0.06
     Moscow
    -0.06
    .**************↵
    -0.06
    Explorer
    -0.06
    NaN
    -0.06
     phong
    -0.06
    ДА
    -0.06
    POSITIVE LOGITS
    (sent
    0.07
     cling
    0.06
     vein
    0.06
    ))?
    0.06
    (Parameter
    0.06
    i
    0.06
    ็นต
    0.06
    enga
    0.06
    error
    0.06
    -handle
    0.06
    Act Density 0.001%

    No Known Activations