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

    Neuronpedia

    INDEX
    Explanations

    mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tostring
    -0.07
    qtt
    -0.07
     Fusion
    -0.07
    ssql
    -0.07
     tsunami
    -0.07
    (Fl
    -0.07
    _OUTPUT
    -0.07
     Tan
    -0.07
     �
    -0.07
    Couldn
    -0.07
    POSITIVE LOGITS
     mark
    0.17
     Mark
    0.16
    Mark
    0.16
    mark
    0.15
    marks
    0.13
     marks
    0.12
    -mark
    0.12
     marking
    0.12
    _mark
    0.12
     Marks
    0.12
    Act Density 0.035%

    No Known Activations