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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VIA
    -0.07
    $action
    -0.06
    Budget
    -0.06
    (sprintf
    -0.06
    ivec
    -0.06
     primeiro
    -0.06
    세요
    -0.06
     mük
    -0.06
    _most
    -0.06
    自身
    -0.06
    POSITIVE LOGITS
     Immun
    0.07
     Nicolas
    0.07
     Grave
    0.06
     fabrication
    0.06
    domains
    0.06
     approaches
    0.06
    よね
    0.06
    umatic
    0.06
    	lbl
    0.06
     embry
    0.06
    Act Density 0.021%

    No Known Activations