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

    Neuronpedia

    INDEX
    Explanations

    movie/book reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rico
    -0.06
     aliqua
    -0.06
     importante
    -0.06
    sort
    -0.06
     Λα
    -0.06
     ship
    -0.06
     centrif
    -0.06
     Given
    -0.06
    resume
    -0.06
     loft
    -0.06
    POSITIVE LOGITS
     strr
    0.07
    ack
    0.07
     只
    0.07
    greSQL
    0.07
    incy
    0.07
     marginBottom
    0.07
     bounced
    0.06
     matt
    0.06
    ματος
    0.06
    <{
    0.06
    Act Density 0.026%

    No Known Activations