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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	RTE
    -0.07
     Side
    -0.07
     Segment
    -0.07
    Command
    -0.07
    PLICATE
    -0.07
    Mixin
    -0.07
     build
    -0.07
    Location
    -0.07
    lexport
    -0.07
    ayan
    -0.07
    POSITIVE LOGITS
    (()=>
    0.06
     of
    0.06
     coop
    0.06
    :i
    0.06
     dreaded
    0.06
     datab
    0.06
     للإ
    0.06
     corrupted
    0.06
    耶
    0.06
    alez
    0.06
    Act Density 0.009%

    No Known Activations