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

    Neuronpedia

    INDEX
    Explanations

    or and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Points
    -0.07
     installation
    -0.07
     isize
    -0.06
    	redirect
    -0.06
    errick
    -0.06
    gt
    -0.06
     pivot
    -0.06
    ynthesis
    -0.06
    (;
    -0.06
     flows
    -0.06
    POSITIVE LOGITS
    >').
    0.06
    име
    0.06
    ۲
    0.06
    성이
    0.06
    戒
    0.06
    γεν
    0.06
    _members
    0.06
     สล
    0.06
    .YEAR
    0.06
    -monitor
    0.06
    Act Density 0.003%

    No Known Activations