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

    Neuronpedia

    INDEX
    Explanations

    tray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    saldo
    -0.07
    ellites
    -0.07
    icerca
    -0.07
    .dsl
    -0.07
    _sphere
    -0.07
     kode
    -0.06
    ectl
    -0.06
     評価
    -0.06
     악
    -0.06
    allel
    -0.06
    POSITIVE LOGITS
     tray
    0.15
     trays
    0.12
     Tray
    0.12
    AY
    0.07
    ray
    0.07
    ay
    0.06
     Tea
    0.06
     typ
    0.06
    Tar
    0.06
     çay
    0.06
    Act Density 0.002%

    No Known Activations