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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	redirect
    -0.07
    _truth
    -0.07
     Mirror
    -0.07
     piece
    -0.07
    decoder
    -0.07
     Zero
    -0.07
     executes
    -0.07
    chnitt
    -0.06
     occasion
    -0.06
    _Long
    -0.06
    POSITIVE LOGITS
    toISOString
    0.06
     aan
    0.06
    ایسه
    0.06
    consum
    0.06
    =ax
    0.06
     همکاری
    0.06
    \Modules
    0.06
    ydro
    0.05
     perpet
    0.05
    .Extensions
    0.05
    Act Density 0.036%

    No Known Activations