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

    Neuronpedia

    INDEX
    Explanations

    album

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Briggs
    -0.08
     summarizes
    -0.07
    Mark
    -0.07
    Anim
    -0.07
     adrenal
    -0.07
     Slow
    -0.06
     ramen
    -0.06
     TMP
    -0.06
    talk
    -0.06
     finest
    -0.06
    POSITIVE LOGITS
    /"↵
    0.07
     ekonomik
    0.06
    '"
    0.06
     телеф
    0.06
    ış
    0.06
    473
    0.06
     производ
    0.06
     своє
    0.06
     groupName
    0.06
     през
    0.06
    Act Density 0.006%

    No Known Activations