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

    Neuronpedia

    INDEX
    Explanations

    gastr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ובי
    -0.08
    -U
    -0.07
    _g
    -0.07
     służ
    -0.07
    _Mod
    -0.07
    <string
    -0.07
     poking
    -0.07
     affirm
    -0.07
     Buck
    -0.07
    _TE
    -0.07
    POSITIVE LOGITS
    RouterModule
    0.08
     gastr
    0.08
    +":
    0.07
    気に
    0.07
     Classical
    0.07
    鳊
    0.07
     Later
    0.07
    Later
    0.07
    faces
    0.07
    喘
    0.07
    Act Density 0.002%

    No Known Activations