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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .monitor
    -0.07
    Regression
    -0.07
     Roland
    -0.07
    Responses
    -0.06
    Mapping
    -0.06
     dependable
    -0.06
    monitor
    -0.06
    培
    -0.06
     solver
    -0.06
    Clazz
    -0.06
    POSITIVE LOGITS
    GtkWidget
    0.07
    lescope
    0.07
    emble
    0.07
     sve
    0.07
    İT
    0.06
    ekkür
    0.06
     wirklich
    0.06
    ικός
    0.06
    ää
    0.06
    τός
    0.06
    Act Density 0.007%

    No Known Activations