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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     женщины
    -0.07
    	mp
    -0.06
    _REV
    -0.06
     firefighters
    -0.06
    ير
    -0.06
    uyu
    -0.06
    216
    -0.06
    �
    -0.06
    Viol
    -0.06
    -CN
    -0.06
    POSITIVE LOGITS
    佳
    0.07
     frying
    0.07
     BYTE
    0.07
     passphrase
    0.07
    �
    0.07
     politician
    0.07
     durumlarda
    0.07
    boxed
    0.07
     "')
    0.06
     Performance
    0.06
    Act Density 0.017%

    No Known Activations