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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seahawks
    -0.06
    І
    -0.06
    もう
    -0.06
    alian
    -0.06
    Editar
    -0.06
    ９
    -0.06
    �
    -0.06
    ４
    -0.06
     подоб
    -0.06
    第二
    -0.06
    POSITIVE LOGITS
     shed
    0.07
     pocket
    0.07
     Logical
    0.07
    plant
    0.07
     extravagant
    0.06
     بوابة
    0.06
    (role
    0.06
     pkg
    0.06
    ACCOUNT
    0.06
     coup
    0.06
    Act Density 0.006%

    No Known Activations