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

    Neuronpedia

    INDEX
    Explanations

    Translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     starving
    -0.08
     wifi
    -0.08
     Fundamentals
    -0.07
    lr
    -0.07
     lancement
    -0.07
     શરૂ
    -0.07
     alimentación
    -0.07
     Curtain
    -0.07
     ontdekken
    -0.07
     सुरू
    -0.07
    POSITIVE LOGITS
    译
    0.18
    訳
    0.17
     traduction
    0.16
     translators
    0.16
     translations
    0.16
     tradução
    0.15
     ترج
    0.15
     translator
    0.15
     translating
    0.15
     traduc
    0.14
    Act Density 0.045%

    No Known Activations