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

    Neuronpedia

    INDEX
    Explanations

    confirming agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    षे
    0.45
    鬃
    0.43
    angu
    0.42
    atmosphère
    0.41
    äm
    0.40
    odies
    0.39
    சிய
    0.38
    clerotic
    0.38
    ainty
    0.38
    धि
    0.37
    POSITIVE LOGITS
     confirmar
    0.40
     confirming
    0.38
     maß
    0.38
    同意
    0.37
    жко
    0.37
     تای
    0.37
     ench
    0.37
     Replica
    0.37
     Grupo
    0.36
     confirma
    0.36
    Act Density 0.000%

    No Known Activations