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

    Neuronpedia

    INDEX
    Explanations

    정

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сло
    -0.07
     привы
    -0.07
     avantaj
    -0.07
     пацієн
    -0.07
     انقل
    -0.07
     entity
    -0.07
     personne
    -0.06
     Skywalker
    -0.06
     puedo
    -0.06
     eigenen
    -0.06
    POSITIVE LOGITS
     congressional
    0.07
     shutting
    0.07
    istinguished
    0.07
    종
    0.07
     MOV
    0.07
     Zig
    0.07
     dopamine
    0.07
    ToolBar
    0.07
    ):
↵
↵
    0.07
     sheriff
    0.07
    Act Density 0.025%

    No Known Activations