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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORIZ
    -0.07
     swinger
    -0.07
    ominator
    -0.07
    _ATTACH
    -0.07
    ldap
    -0.07
     nitel
    -0.06
     aspiring
    -0.06
     văn
    -0.06
    озя
    -0.06
    <!--↵
    -0.06
    POSITIVE LOGITS
     Rank
    0.07
    thers
    0.07
    ैं।
    0.07
     U
    0.07
     RBI
    0.06
    _co
    0.06
    }");↵↵
    0.06
     dy
    0.06
     Tanrı
    0.06
    daş
    0.06
    Act Density 0.022%

    No Known Activations