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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     %=
    -0.06
     Ars
    -0.06
     pregunta
    -0.06
    student
    -0.06
    publisher
    -0.06
     визнача
    -0.06
    ảm
    -0.06
     aider
    -0.06
    selector
    -0.06
    alli
    -0.06
    POSITIVE LOGITS
    _CART
    0.07
    :null
    0.06
     gdy
    0.06
    テル
    0.06
    _tick
    0.06
     були
    0.06
     awesome
    0.06
     hardcore
    0.06
    .ENTER
    0.06
    .depth
    0.06
    Act Density 0.001%

    No Known Activations