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

    Neuronpedia

    INDEX
    Explanations

    Code/software files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Objective
    -0.06
     جمهور
    -0.06
     occupancy
    -0.06
     Beer
    -0.06
    ̈
    -0.06
    .MATCH
    -0.06
     BUY
    -0.06
     Continuing
    -0.06
    Qty
    -0.06
    isky
    -0.06
    POSITIVE LOGITS
     dwar
    0.08
     mik
    0.07
    #endif
    0.06
     foul
    0.06
     guides
    0.06
    792
    0.06
    .microsoft
    0.06
     infring
    0.06
    技能
    0.06
    zburg
    0.06
    Act Density 0.006%

    No Known Activations