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

    Neuronpedia

    INDEX
    Explanations

    .Mutex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     save
    -0.07
    -standard
    -0.07
     saved
    -0.07
    +"
    -0.07
    rne
    -0.07
    ":
    -0.07
     Partner
    -0.07
    헌
    -0.06
     home
    -0.06
    =>'
    -0.06
    POSITIVE LOGITS
     birik
    0.07
     môn
    0.06
     radiator
    0.06
    ým
    0.06
    Extern
    0.06
    IAM
    0.06
     kış
    0.05
     athletes
    0.05
    .getItemId
    0.05
     Sally
    0.05
    Act Density 0.003%

    No Known Activations