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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    汽车
    -0.07
    iliz
    -0.06
    同意
    -0.06
     Kan
    -0.06
     Rc
    -0.06
    nym
    -0.06
    .Debugger
    -0.05
     residences
    -0.05
    	head
    -0.05
    общ
    -0.05
    POSITIVE LOGITS
    IMAGE
    0.07
    sent
    0.07
    cimal
    0.07
    rang
    0.06
    (expected
    0.06
     genera
    0.06
    .factory
    0.06
     Marco
    0.06
    leo
    0.06
     Craig
    0.06
    Act Density 0.007%

    No Known Activations