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
    -aging
    -0.08
    -smart
    -0.08
     moms
    -0.07
    -empty
    -0.07
    .wikipedia
    -0.07
     funger
    -0.07
     принима
    -0.07
    -0.07
     <-
    -0.07
    lopende
    -0.07
    POSITIVE LOGITS
    Seb
    0.08
    Const
    0.08
    亞
    0.08
     七
    0.08
     Seb
    0.08
    784
    0.07
     Const
    0.07
    183
    0.07
    182
    0.07
    CONST
    0.07
    Act Density 0.096%
    No Known Activations