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

    Neuronpedia

    INDEX
    Explanations

    field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barg
    -0.07
     implement
    -0.07
    getResponse
    -0.06
     race
    -0.06
    协
    -0.06
    layan
    -0.06
    「お
    -0.06
     contrace
    -0.06
     intimate
    -0.06
    pivot
    -0.06
    POSITIVE LOGITS
    MainWindow
    0.07
    营
    0.07
    Clr
    0.07
     libs
    0.07
    >/
    0.07
     Guidelines
    0.07
     Ministry
    0.07
     hold
    0.07
    MD
    0.06
     світ
    0.06
    Act Density 0.009%

    No Known Activations