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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lobs
    -0.29
    composite
    -0.27
    å¿ĺ
    -0.26
    lems
    -0.25
    path
    -0.25
    oming
    -0.24
     wheel
    -0.24
    åħ¨åªĴä½ĵ
    -0.24
    wheel
    -0.24
     monetary
    -0.24
    POSITIVE LOGITS
    è¯ĬæīĢ
    0.28
    ç¿Ļ
    0.27
     Env
    0.26
    chai
    0.25
    olin
    0.25
     setattr
    0.25
    åĨįçĶŁ
    0.25
    Inject
    0.25
    纳
    0.24
     clim
    0.24
    Act Density 0.003%

    No Known Activations