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

    Neuronpedia

    INDEX
    Explanations

    word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accusations
    -0.07
    Estado
    -0.07
     '"
    -0.07
    MAC
    -0.07
     cara
    -0.06
     Luz
    -0.06
     tiện
    -0.06
     scenarios
    -0.06
    ائية
    -0.06
     geographic
    -0.06
    POSITIVE LOGITS
    (outputs
    0.07
    lemn
    0.07
    =back
    0.06
    ґ
    0.06
    ishments
    0.06
    =sc
    0.06
     subtract
    0.06
    =explode
    0.06
     parsed
    0.06
     уклад
    0.06
    Act Density 0.093%

    No Known Activations