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

    Neuronpedia

    INDEX
    Explanations

    explicit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qr
    -0.07
    áveis
    -0.07
     (*(
    -0.07
    eygamber
    -0.07
     월세
    -0.07
     tx
    -0.07
    -е
    -0.07
    (LED
    -0.06
    ’den
    -0.06
    işti
    -0.06
    POSITIVE LOGITS
    	explicit
    0.07
    ogue
    0.07
    Josh
    0.07
     hook
    0.07
     notify
    0.07
     explicit
    0.07
     tag
    0.06
     Spo
    0.06
     fraud
    0.06
    lak
    0.06
    Act Density 0.001%

    No Known Activations