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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }))
    -0.07
    	HANDLE
    -0.06
    ']])↵
    -0.06
     ReadOnly
    -0.06
     wizards
    -0.06
    leaders
    -0.06
     Bella
    -0.06
    ishop
    -0.06
    可谓是
    -0.06
     scouting
    -0.06
    POSITIVE LOGITS
    ᖇ
    0.08
     thói
    0.07
    ensation
    0.07
     carro
    0.07
    .err
    0.07
    එ
    0.07
    봣
    0.07
    俄军
    0.07
     repairs
    0.07
    昫
    0.07
    Act Density 0.114%

    No Known Activations