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

    Neuronpedia

    INDEX
    Explanations

    diagonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .account
    -0.08
     account
    -0.08
     lán
    -0.08
     relacionada
    -0.08
     spectacle
    -0.08
    给予
    -0.08
     grooming
    -0.07
     recruitment
    -0.07
     സംബന്ധ
    -0.07
    ್ತ
    -0.07
    POSITIVE LOGITS
     diagon
    0.10
     halves
    0.10
    _sprite
    0.09
     કો�
    0.08
     diagonal
    0.08
    quarter
    0.08
    Diagonal
    0.08
    _HALF
    0.08
    prite
    0.08
     rectangular
    0.08
    Act Density 0.014%

    No Known Activations