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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obe
    -0.07
    maya
    -0.07
     letech
    -0.06
    rogram
    -0.06
     Implicit
    -0.06
    -half
    -0.06
     ante
    -0.06
     сч
    -0.06
     embodied
    -0.06
     hodnot
    -0.06
    POSITIVE LOGITS
    Ens
    0.07
     Fully
    0.07
    597
    0.06
     Jets
    0.06
    parms
    0.06
    Instr
    0.06
    _YELLOW
    0.06
     write
    0.06
    Nit
    0.06
     reduction
    0.06
    Act Density 0.001%

    No Known Activations