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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dom
    -0.07
     Cent
    -0.06
     kang
    -0.06
    ordinated
    -0.06
    .restaurant
    -0.06
     decades
    -0.06
     Chr
    -0.06
     Sergei
    -0.06
    Hier
    -0.06
     shar
    -0.06
    POSITIVE LOGITS
    ">$
    0.06
    Bootstrap
    0.06
     findOne
    0.06
     POLITICO
    0.06
     Assange
    0.06
    ाम
    0.06
    	initialize
    0.06
    person
    0.06
     حافظ
    0.05
     anv
    0.05
    Act Density 0.005%

    No Known Activations