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

    Neuronpedia

    INDEX
    Explanations

    data and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mux
    -0.08
    wo
    -0.07
    ัฒ
    -0.06
    říz
    -0.06
    安装
    -0.06
    bcrypt
    -0.06
     Deus
    -0.06
    yh
    -0.06
    telephone
    -0.06
     StartTime
    -0.06
    POSITIVE LOGITS
     Evel
    0.07
    -toast
    0.06
    のか
    0.06
    ated
    0.06
    ViewModel
    0.06
     Aware
    0.06
    }`).
    0.06
    631
    0.06
     dearly
    0.06
    Poly
    0.05
    Act Density 0.000%

    No Known Activations