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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     functionality
    -0.08
     orient
    -0.08
     हल
    -0.08
     Idee
    -0.07
     phải
    -0.07
    .easy
    -0.07
     prze
    -0.07
     corporal
    -0.07
     Becky
    -0.07
     Orientation
    -0.07
    POSITIVE LOGITS
     Guaranteed
    0.10
     Reserved
    0.10
     suministro
    0.09
    供
    0.09
     guaranteed
    0.09
     מראש
    0.09
    _RESERVED
    0.09
     固
    0.09
    Guarante
    0.09
    _supply
    0.09
    Act Density 0.014%

    No Known Activations