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

    Neuronpedia

    INDEX
    Explanations

    Ce, Bi, PLA, earth elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.80
    th
    0.79
    er
    0.77
    il
    0.77
    j
    0.75
    k
    0.75
    la
    0.73
    r
    0.73
    lof
    0.71
    i
    0.70
    POSITIVE LOGITS
    ートン
    0.64
     methodical
    0.61
    etten
    0.59
    мни
    0.59
     équipes
    0.59
     majesty
    0.59
    过程中
    0.58
    на
    0.58
     walks
    0.57
    ０
    0.57
    Act Density 0.001%

    No Known Activations