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

    Neuronpedia

    INDEX
    Explanations

    you know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ទៀត
    0.38
    均
    0.37
     ufficiale
    0.37
     correttamente
    0.37
     ચૂક
    0.37
     ligados
    0.37
     notations
    0.36
     reconhecimento
    0.36
     dahulu
    0.36
    ⢿
    0.36
    POSITIVE LOGITS
     know
    1.28
    know
    1.20
    Know
    1.03
     Know
    0.99
    知
    0.84
     biết
    0.71
    知道
    0.69
     knows
    0.67
     Knowles
    0.67
     savoir
    0.64
    Act Density 0.006%

    No Known Activations