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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	check
    -0.07
     Duck
    -0.07
    -resources
    -0.06
     Breath
    -0.06
     身
    -0.06
     Urb
    -0.06
     akan
    -0.06
    Frozen
    -0.06
     Besch
    -0.06
     字
    -0.06
    POSITIVE LOGITS
     mutual
    0.07
    ULE
    0.07
    Animations
    0.07
    Inlining
    0.07
    gte
    0.07
    。<
    0.06
     unanim
    0.06
     mutually
    0.06
    :"",↵
    0.06
     turbulent
    0.06
    Act Density 0.188%

    No Known Activations