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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	en
    -0.07
    _entry
    -0.07
     Congratulations
    -0.06
     debian
    -0.06
     plant
    -0.06
     Printing
    -0.06
     printing
    -0.06
     Completed
    -0.06
    instagram
    -0.06
     snake
    -0.06
    POSITIVE LOGITS
    _cd
    0.07
     calmly
    0.07
    datap
    0.06
     pří
    0.06
     каб
    0.06
    "
↵
↵
    0.06
     pasado
    0.06
     damp
    0.06
    POCH
    0.06
     cyk
    0.06
    Act Density 0.008%

    No Known Activations