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

    Neuronpedia

    INDEX
    Explanations

    Employee classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     külön
    -0.09
    alle
    -0.08
    碎
    -0.08
    不同
    -0.08
    까지
    -0.08
     വരെ
    -0.08
     حصہ
    -0.08
    欣
    -0.08
     stamina
    -0.08
     performances
    -0.07
    POSITIVE LOGITS
     tratado
    0.08
     improperly
    0.08
     configur
    0.08
    Trat
    0.08
     doctr
    0.08
     clarification
    0.08
     classific
    0.08
     prea
    0.08
     appelle
    0.08
     판단
    0.08
    Act Density 0.014%

    No Known Activations