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

    Neuronpedia

    INDEX
    Explanations

    concrete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    approximately
    -0.07
    vature
    -0.07
    LineWidth
    -0.07
    학교
    -0.07
    ubu
    -0.06
    -strong
    -0.06
    lifetime
    -0.06
     strong
    -0.06
    Hallo
    -0.06
    important
    -0.06
    POSITIVE LOGITS
     $('#'
    0.07
     Data
    0.07
    	cp
    0.06
     حذف
    0.06
    ↵    ↵
    0.06
     optim
    0.06
    dehy
    0.06
     jednoho
    0.06
    ในช
    0.06
    Ars
    0.06
    Act Density 0.189%

    No Known Activations