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

    Neuronpedia

    INDEX
    Explanations

    varied text types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Going
    -0.07
    Î
    -0.07
    eps
    -0.06
     英
    -0.06
    	uv
    -0.06
     авг
    -0.06
    วน
    -0.05
     สม
    -0.05
    هن
    -0.05
     vous
    -0.05
    POSITIVE LOGITS
    Router
    0.08
     notebook
    0.08
    erosis
    0.07
     Logout
    0.07
     law
    0.07
    924
    0.07
     Law
    0.07
     koc
    0.07
     discussing
    0.07
     Renderer
    0.07
    Act Density 0.000%

    No Known Activations