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

    Neuronpedia

    INDEX
    Explanations

    blog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fold
    -0.07
    监督
    -0.07
    _drive
    -0.07
     plug
    -0.07
     UNITY
    -0.06
    THEN
    -0.06
    HWND
    -0.06
     POINT
    -0.06
    .Head
    -0.06
     discriminatory
    -0.06
    POSITIVE LOGITS
    idelity
    0.06
     Israeli
    0.06
     Macy
    0.06
    ."),
    0.06
     Islamic
    0.06
     FTC
    0.06
     eventos
    0.06
    帕
    0.06
    _blocked
    0.06
    辑
    0.06
    Act Density 0.019%

    No Known Activations