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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owed
    -0.07
    اور
    -0.06
    ANS
    -0.06
     女
    -0.06
    Thickness
    -0.06
     تمام
    -0.06
    aste
    -0.06
     bowed
    -0.06
     nuova
    -0.06
    해
    -0.06
    POSITIVE LOGITS
    (Encoding
    0.07
    ίναι
    0.06
    只
    0.06
    	emit
    0.06
    -peer
    0.06
    】,【
    0.06
    ター
    0.06
    inkel
    0.06
                ↵
    0.06
     CORE
    0.06
    Act Density 0.005%

    No Known Activations