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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gra
    -0.07
     Від
    -0.07
    moon
    -0.06
    wheel
    -0.06
    mailer
    -0.06
    ується
    -0.06
     sacrificing
    -0.06
    ायल
    -0.06
     sahip
    -0.06
    ablo
    -0.06
    POSITIVE LOGITS
     yeri
    0.07
     abandoning
    0.07
     half
    0.06
    _void
    0.06
     BASIC
    0.06
     semi
    0.06
     labor
    0.06
    ﻴ
    0.06
    Accessory
    0.06
    launch
    0.06
    Act Density 0.049%

    No Known Activations