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

    Neuronpedia

    INDEX
    Explanations

    of for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kidd
    -0.06
    ("");↵
    -0.06
     çalışmalar
    -0.06
     '''↵↵
    -0.06
     """↵↵
    -0.06
     challeng
    -0.06
    405
    -0.06
    stories
    -0.06
     Hentai
    -0.06
     chicago
    -0.06
    POSITIVE LOGITS
    acje
    0.07
    avou
    0.07
     Applying
    0.06
    Sie
    0.06
    ,rp
    0.06
    resher
    0.06
     revoked
    0.06
     revived
    0.06
    Packet
    0.06
     Applicant
    0.06
    Act Density 0.026%

    No Known Activations