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

    Neuronpedia

    INDEX
    Explanations

    goals and objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RECOMM
    0.35
     wacht
    0.35
     yum
    0.34
    EVERY
    0.34
    ouched
    0.33
     EVERY
    0.33
    Executed
    0.32
     хорошие
    0.32
     când
    0.32
     warfarin
    0.31
    POSITIVE LOGITS
     goals
    1.34
     objectives
    1.24
     requirements
    1.16
     Goals
    1.16
    goals
    1.16
     objectifs
    1.13
     objetivos
    1.12
     целей
    1.12
    Goals
    1.10
     목표
    1.10
    Act Density 0.065%

    No Known Activations