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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fsp
    -0.07
     Souls
    -0.07
     ansatte
    -0.07
     ))
    -0.07
     overseeing
    -0.07
     atrás
    -0.07
    Contacts
    -0.07
     Contacts
    -0.07
     calculated
    -0.07
     }↵↵↵//
    -0.07
    POSITIVE LOGITS
     alsnog
    0.11
     부탁
    0.10
     clarification
    0.10
    才能
    0.09
     inputs
    0.09
    输入
    0.08
     terlebih
    0.08
     clar
    0.08
     vollständ
    0.08
     नी
    0.08
    Act Density 0.024%

    No Known Activations