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

    Neuronpedia

    INDEX
    Explanations

    die casting molds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     waged
    0.75
    +.
    0.72
    \}\
    0.67
    ,{
    0.67
    )`,
    0.65
    MEAN
    0.65
     there
    0.64
     HAVE
    0.64
     +.
    0.64
     syllable
    0.63
    POSITIVE LOGITS
    age
    0.93
    at
    0.93
    ete
    0.89
    ia
    0.86
    um
    0.80
    ков
    0.76
    et
    0.73
    iken
    0.73
    ุ
    0.73
    ile
    0.73
    Act Density 0.001%

    No Known Activations