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

    Neuronpedia

    INDEX
    Explanations

    commitment and initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     제거
    0.77
     birbir
    0.76
     verhindert
    0.75
     confine
    0.75
    ってしまう
    0.75
     varsa
    0.72
     verhindern
    0.71
     parasit
    0.71
     MATHEMAT
    0.71
     Archim
    0.71
    POSITIVE LOGITS
     initiatives
    1.88
     commitment
    1.76
     commitments
    1.67
     iniciativas
    1.63
     Initiatives
    1.59
     efforts
    1.58
    commitment
    1.54
     Commitment
    1.53
     प्रतिबद्ध
    1.52
    取り組み
    1.50
    Act Density 0.177%

    No Known Activations