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

    Neuronpedia

    INDEX
    Explanations

    ability to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    je
    0.43
     enigmatic
    0.41
     chaqueta
    0.41
     imaginar
    0.40
     ambiguity
    0.40
     noyau
    0.40
     zwei
    0.40
     amorphous
    0.40
     eliminación
    0.39
     ambiguous
    0.39
    POSITIVE LOGITS
     participate
    0.54
    参与
    0.53
     partake
    0.53
    參與
    0.50
     access
    0.45
     полноцен
    0.45
    ใช้งาน
    0.44
    正常
    0.43
     acceder
    0.43
     mengakses
    0.43
    Act Density 0.167%

    No Known Activations