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

    Neuronpedia

    INDEX
    Explanations

    Emphasis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vs
    -0.07
     coffin
    -0.07
    "c
    -0.07
     getValue
    -0.06
     п
    -0.06
     smarter
    -0.06
    	prop
    -0.06
    Wrong
    -0.06
     quadratic
    -0.06
     vegetables
    -0.06
    POSITIVE LOGITS
     extremely
    0.07
     громадян
    0.06
    .rb
    0.06
    .internet
    0.06
     фактор
    0.06
    Elizabeth
    0.06
     really
    0.06
     UNIX
    0.06
     chế
    0.06
    OPTION
    0.06
    Act Density 0.123%

    No Known Activations