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

    Neuronpedia

    INDEX
    Explanations

    the followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হাদী
    0.67
     eten
    0.67
    away
    0.67
     Biochim
    0.66
     Korea
    0.65
     отмети
    0.65
     Away
    0.64
     σημ
    0.64
     sconf
    0.64
     값을
    0.63
    POSITIVE LOGITS
     breasts
    0.90
     several
    0.83
     bosom
    0.78
    several
    0.78
    ныя
    0.74
     faculty
    0.72
     generality
    0.70
    指导
    0.68
     breast
    0.68
     renovating
    0.68
    Act Density 0.014%

    No Known Activations