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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eil
    -0.07
     hbox
    -0.07
    "><?
    -0.06
    .cleanup
    -0.06
    iaux
    -0.06
     США
    -0.06
    (<?
    -0.06
     +/-
    -0.06
    >({
    -0.06
    塚
    -0.06
    POSITIVE LOGITS
     Collision
    0.07
     filtering
    0.07
     corp
    0.06
    ernes
    0.06
     overlap
    0.06
    occo
    0.06
     synthetic
    0.06
     Alternatively
    0.06
    lg
    0.06
    測
    0.06
    Act Density 0.000%

    No Known Activations