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

    Neuronpedia

    INDEX
    Explanations

    PHP mailing errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .provider
    -0.07
    Oct
    -0.06
     Lyrics
    -0.06
     �
    -0.06
    Bru
    -0.06
    utsch
    -0.06
    会议
    -0.06
    &nbsp
    -0.05
     Responsibilities
    -0.05
     sui
    -0.05
    POSITIVE LOGITS
     같은
    0.08
    %'↵
    0.07
     hides
    0.07
    ัวเอง
    0.06
     ativ
    0.06
     signaled
    0.06
    مارات
    0.06
    OLUMN
    0.06
     등의
    0.06
    argout
    0.06
    Act Density 0.006%

    No Known Activations