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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pink
    -0.07
     FIR
    -0.06
    ']:↵
    -0.06
     protest
    -0.06
     pnl
    -0.06
     emin
    -0.06
    SUR
    -0.06
     civic
    -0.06
    union
    -0.06
     Tray
    -0.06
    POSITIVE LOGITS
    iere
    0.07
    issing
    0.07
     initializing
    0.07
    bc
    0.06
     uzak
    0.06
    اون
    0.06
    exchange
    0.06
    ้าพ
    0.06
    กรรมการ
    0.06
    .Serialize
    0.06
    Act Density 0.022%

    No Known Activations