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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فأ
    -0.07
    ecome
    -0.06
     anche
    -0.06
     mpg
    -0.06
    UTES
    -0.06
     malé
    -0.06
    keeper
    -0.06
    yards
    -0.06
     λα
    -0.06
     أو
    -0.06
    POSITIVE LOGITS
     familia
    0.07
     �
    0.07
     {}),↵
    0.07
    `)↵
    0.07
     successful
    0.07
     foreign
    0.07
     erotiske
    0.06
     certainty
    0.06
    ');↵
    0.06
    $html
    0.06
    Act Density 0.020%

    No Known Activations