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

    Neuronpedia

    INDEX
    Explanations

    Stepwise regression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _f
    -0.06
     analys
    -0.06
    _DISPATCH
    -0.06
     ана
    -0.06
     u
    -0.06
    传出
    -0.06
    b
    -0.06
    pickup
    -0.06
     ********************************************************************************
    -0.06
    قدم
    -0.06
    POSITIVE LOGITS
    kreśl
    0.07
    洛杉
    0.07
     moż
    0.07
    .real
    0.07
    Howard
    0.06
     authored
    0.06
    굉
    0.06
    馉
    0.06
    .blur
    0.06
    CharCode
    0.06
    Act Density 0.001%

    No Known Activations