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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    let
    -0.08
     mam
    -0.07
     method
    -0.07
     obtains
    -0.07
    $t
    -0.07
    ior
    -0.07
     ап
    -0.07
    只
    -0.07
    	T
    -0.07
    ,Object
    -0.07
    POSITIVE LOGITS
     across
    0.10
     Across
    0.09
    Across
    0.09
     face
    0.07
    Cross
    0.07
    CAP
    0.07
    ика
    0.07
     澳
    0.06
    icro
    0.06
    isku
    0.06
    Act Density 0.018%

    No Known Activations