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

    Neuronpedia

    INDEX
    Explanations

    https

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catastrophic
    -0.07
     BRO
    -0.06
    rut
    -0.06
    _TypeInfo
    -0.06
    เฟ
    -0.06
     lu
    -0.06
    (Arg
    -0.06
    	Date
    -0.06
    िल
    -0.06
    utility
    -0.06
    POSITIVE LOGITS
     smiled
    0.07
     operates
    0.07
    cessive
    0.06
    کاری
    0.06
    élé
    0.06
     Mein
    0.06
     campaigned
    0.06
     certains
    0.06
     serializer
    0.06
     operate
    0.05
    Act Density 0.009%

    No Known Activations