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
     shades
    -0.08
     təqdim
    -0.08
     foy
    -0.08
     tərəfindən
    -0.08
     renewable
    -0.08
    aching
    -0.08
     delays
    -0.07
     tipi
    -0.07
    سبق
    -0.07
     və
    -0.07
    POSITIVE LOGITS
     equation
    0.11
    Equation
    0.11
    Equality
    0.11
     equality
    0.10
     equations
    0.10
     Equation
    0.09
     Equality
    0.09
     lhs
    0.09
     condition
    0.09
     fordert
    0.08
    Act Density 0.117%

    No Known Activations