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

    Neuronpedia

    INDEX
    Explanations

    acronym "PT"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gas
    -0.07
    -war
    -0.07
     kW
    -0.07
     GAM
    -0.07
    泽
    -0.07
     Harris
    -0.06
    ーブル
    -0.06
    weapons
    -0.06
     бак
    -0.06
    ARB
    -0.06
    POSITIVE LOGITS
     PT
    0.16
     pt
    0.13
    PT
    0.13
    pt
    0.12
    ft
    0.10
    Pt
    0.10
     Pt
    0.10
    .pt
    0.10
    _pt
    0.10
    FT
    0.09
    Act Density 0.009%

    No Known Activations