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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    پ
    -0.07
     або
    -0.07
    	hr
    -0.06
     bedding
    -0.06
    NUM
    -0.06
    MITTED
    -0.06
    Tac
    -0.06
    ENTS
    -0.06
    enting
    -0.06
    larına
    -0.06
    POSITIVE LOGITS
    ประเภท
    0.07
     memcpy
    0.06
     Furious
    0.06
    猫
    0.06
     CBS
    0.06
    Jeremy
    0.06
     Liste
    0.06
     τρο
    0.06
    -person
    0.06
     }
↵
↵
    0.06
    Act Density 0.149%

    No Known Activations