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

    Neuronpedia

    INDEX
    Explanations

    ashire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kd
    -0.06
    [j
    -0.06
     drift
    -0.06
    .sd
    -0.06
     Couldn
    -0.06
    -road
    -0.06
     Beng
    -0.06
     Oh
    -0.06
     d
    -0.06
    Kn
    -0.06
    POSITIVE LOGITS
    ure
    0.12
    URE
    0.11
    are
    0.11
    atore
    0.11
    ARE
    0.11
    ore
    0.11
    ire
    0.11
    urre
    0.10
    re
    0.10
     Gore
    0.09
    Act Density 0.194%

    No Known Activations