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

    Neuronpedia

    INDEX
    Explanations

    accessing device APIs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TEXT
    -0.07
    /etc
    -0.07
     לוקח
    -0.07
    퓪
    -0.06
    ,.↵↵
    -0.06
    第一章
    -0.06
    Leaks
    -0.06
     TableCell
    -0.06
    Justin
    -0.06
     Checked
    -0.06
    POSITIVE LOGITS
     dựng
    0.08
    _dw
    0.07
     updates
    0.07
    connections
    0.07
    分销
    0.07
     posible
    0.06
     imperfect
    0.06
    .rpm
    0.06
     activ
    0.06
     shells
    0.06
    Act Density 0.053%

    No Known Activations