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

    Neuronpedia

    INDEX
    Explanations

    numbers and specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensen
    -0.07
    ланд
    -0.07
     Judaism
    -0.07
     Assign
    -0.07
    лам
    -0.07
    ested
    -0.07
     Lori
    -0.06
    isEmpty
    -0.06
    ۱۶
    -0.06
    getToken
    -0.06
    POSITIVE LOGITS
    ][_
    0.06
    तर
    0.06
    辆
    0.05
     smoother
    0.05
     LAB
    0.05
     //↵
    0.05
    IGIN
    0.05
     viewpoints
    0.05
     PEN
    0.05
    caffold
    0.05
    Act Density 0.187%

    No Known Activations