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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '))↵↵
    -0.07
    �
    -0.06
    Starting
    -0.06
     Adv
    -0.06
    느
    -0.06
     Veg
    -0.06
    циклопед
    -0.06
    Investigators
    -0.06
     Zem
    -0.06
    deer
    -0.06
    POSITIVE LOGITS
     sophisticated
    0.07
     вари
    0.07
     SHIFT
    0.06
    átu
    0.06
     leftist
    0.06
     uydu
    0.06
     فارس
    0.06
     idx
    0.06
    _TYPEDEF
    0.06
     ':'
    0.06
    Act Density 0.006%

    No Known Activations