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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anned
    -0.07
     Clintons
    -0.07
    Tri
    -0.07
    loads
    -0.07
    .lib
    -0.07
     请求
    -0.06
    DIR
    -0.06
     Unidos
    -0.06
    _lit
    -0.06
    Ratio
    -0.06
    POSITIVE LOGITS
     Acer
    0.06
    paque
    0.06
     applying
    0.06
     segunda
    0.06
     Cement
    0.06
    .instrument
    0.06
    :NSLocalizedString
    0.06
     newbie
    0.05
    mist
    0.05
    ائل
    0.05
    Act Density 0.022%

    No Known Activations