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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    学生
    -0.07
    Effects
    -0.07
     fibers
    -0.06
    Rh
    -0.06
    	act
    -0.06
    .camera
    -0.06
    ільш
    -0.06
    чик
    -0.06
     volcanic
    -0.06
    Directory
    -0.06
    POSITIVE LOGITS
    357
    0.07
     Ston
    0.06
    :
    0.06
    igned
    0.06
    appoint
    0.06
    ATOM
    0.06
     acquaint
    0.06
     Made
    0.06
    ρκεια
    0.06
     Communities
    0.06
    Act Density 0.011%

    No Known Activations