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

    Neuronpedia

    INDEX
    Explanations

    Introductions and welcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (foo
    -0.07
    12
    -0.06
    169
    -0.06
     problematic
    -0.06
    apid
    -0.06
    /student
    -0.06
     SMART
    -0.06
    042
    -0.06
    oust
    -0.06
     forced
    -0.06
    POSITIVE LOGITS
     buddy
    0.07
    _ws
    0.07
    brıs
    0.06
    .ptr
    0.06
    ZeroWidthSpace
    0.06
    eker
    0.06
     dří
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
     colder
    0.06
    StyleSheet
    0.06
    Act Density 0.067%

    No Known Activations