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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (selector
    -0.06
    _ordered
    -0.06
    anzeigen
    -0.06
    허
    -0.06
    	Matrix
    -0.06
    .Restrict
    -0.06
     founding
    -0.06
     �
    -0.06
    ों,
    -0.06
     thường
    -0.06
    POSITIVE LOGITS
     澳
    0.07
    nesia
    0.07
     exemp
    0.07
     Anglic
    0.06
    ='../
    0.06
    SingleOrDefault
    0.06
    caught
    0.06
    <source
    0.06
    PL
    0.06
    iske
    0.06
    Act Density 0.008%

    No Known Activations