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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	border
    -0.06
    ثل
    -0.06
    (hr
    -0.06
    -your
    -0.06
    ози
    -0.06
    currency
    -0.06
     Laura
    -0.06
    <img
    -0.06
    dbg
    -0.06
    ursion
    -0.06
    POSITIVE LOGITS
    groupon
    0.08
     Apprent
    0.07
    .finished
    0.07
     pakistan
    0.06
    pped
    0.06
     favor
    0.06
    .fixed
    0.06
     kims
    0.06
    (",")↵
    0.06
    NotEmpty
    0.06
    Act Density 0.000%

    No Known Activations