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

    Neuronpedia

    INDEX
    Explanations

    strategic plans and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.98
    oben
    0.96
    য়ান
    0.95
     Mares
    0.94
    ᱶ
    0.91
    illance
    0.90
     Fehl
    0.90
     buiten
    0.90
    mathrm
    0.89
    ၉
    0.89
    POSITIVE LOGITS
    न
    1.17
    窠
    1.04
    годи
    1.01
    ،
    1.01
    ون
    1.00
    Ning
    0.97
    ان
    0.96
     страте
    0.96
    nings
    0.96
    Ꮹ
    0.95
    Act Density 0.032%

    No Known Activations