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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lvl
    -0.07
     기준
    -0.06
    	board
    -0.06
    (urls
    -0.06
     ORM
    -0.06
     وقت
    -0.06
    anguard
    -0.06
    рім
    -0.06
     초
    -0.06
    설
    -0.06
    POSITIVE LOGITS
    issement
    0.06
     Reserved
    0.06
    .when
    0.06
    resultado
    0.06
    真的
    0.06
     injected
    0.06
    -Ray
    0.06
     guides
    0.06
     terror
    0.06
     TLabel
    0.06
    Act Density 0.015%

    No Known Activations