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

    Neuronpedia

    INDEX
    Explanations

    customer service complaints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fingert
    -0.07
    ested
    -0.06
     Ella
    -0.06
    stopped
    -0.06
    哥
    -0.06
     YORK
    -0.06
     MAK
    -0.06
    model
    -0.06
    ków
    -0.06
    256
    -0.06
    POSITIVE LOGITS
    BUTTONDOWN
    0.07
    ]+
    0.07
    exampleModalLabel
    0.06
    然而
    0.06
     disastr
    0.06
     sürede
    0.06
     wiring
    0.06
    centaje
    0.06
     nguy
    0.06
    Hundreds
    0.06
    Act Density 0.049%

    No Known Activations