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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Far
    -0.07
    FOUNDATION
    -0.07
    <header
    -0.07
    }}],↵
    -0.07
    usercontent
    -0.07
    �
    -0.06
    UNDER
    -0.06
    独自
    -0.06
    撕
    -0.06
     dialogRef
    -0.06
    POSITIVE LOGITS
     MG
    0.07
    .cp
    0.07
     التجارية
    0.07
    냈
    0.07
    ;'>
    0.07
    полнить
    0.06
    폈
    0.06
    핫
    0.06
     geçen
    0.06
     dirección
    0.06
    Act Density 0.001%

    No Known Activations