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

    Neuronpedia

    INDEX
    Explanations

    man followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    なった
    0.53
    ᐊ
    0.51
    pont
    0.50
     diterapkan
    0.49
    віт
    0.49
     berfungsi
    0.48
    짙
    0.48
    current
    0.48
    成分
    0.47
    الد
    0.47
    POSITIVE LOGITS
    জমেন্ট
    0.82
    ifolds
    0.80
    hattan
    0.80
     pedibusque
    0.79
     マン
    0.78
    agment
    0.75
    끽
    0.73
     mano
    0.68
     Madness
    0.68
    uels
    0.66
    Act Density 0.143%

    No Known Activations