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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     underage
    -0.06
     smlouvy
    -0.06
     нерв
    -0.06
     عاشق
    -0.06
    GroupName
    -0.06
    ;|
    -0.06
    álním
    -0.06
     поскольку
    -0.06
    عنوان
    -0.06
     mM
    -0.06
    POSITIVE LOGITS
    h
    0.07
    08
    0.07
     Bravo
    0.06
    esc
    0.06
     Apprent
    0.06
     lever
    0.06
    .Scan
    0.06
     Impossible
    0.06
    des
    0.06
     Barth
    0.06
    Act Density 0.002%

    No Known Activations