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

    Neuronpedia

    INDEX
    Explanations

    Introduces explanation or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cluding
    0.40
    YPE
    0.40
     Including
    0.40
    ensee
    0.37
     including
    0.36
     direct
    0.36
     chon
    0.35
     arrang
    0.35
     incluindo
    0.34
     fluct
    0.33
    POSITIVE LOGITS
     entails
    1.06
     involves
    0.98
     necessitates
    0.91
     entail
    0.89
     requires
    0.86
     требует
    0.83
     innebär
    0.83
     necessitate
    0.82
    requires
    0.81
     entailed
    0.81
    Act Density 0.004%

    No Known Activations