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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iteration
    -0.06
     representing
    -0.06
     miners
    -0.06
    hours
    -0.06
    URI
    -0.06
     Winner
    -0.06
     다양한
    -0.06
    —are
    -0.06
    -ce
    -0.06
    udge
    -0.06
    POSITIVE LOGITS
    oz
    0.07
    .Append
    0.07
     planned
    0.07
    ?p
    0.06
    zin
    0.06
     stabbed
    0.06
    猫
    0.06
     AppDelegate
    0.06
    ΑΓ
    0.06
    _tar
    0.06
    Act Density 0.009%

    No Known Activations