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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tips
    -0.08
     wafer
    -0.08
    terminated
    -0.08
    работ
    -0.07
     teammate
    -0.07
     Parl
    -0.07
     അറ
    -0.07
    serv
    -0.07
     Guards
    -0.07
    Serv
    -0.07
    POSITIVE LOGITS
     attribut
    0.14
     atrib
    0.13
     attribution
    0.13
     atribu
    0.12
     Attribution
    0.11
     attributed
    0.11
     inaccur
    0.10
     blame
    0.10
     attribute
    0.10
     incorrectly
    0.10
    Act Density 0.076%

    No Known Activations