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

    Neuronpedia

    INDEX
    Explanations

    Okay, following comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     foolproof
    0.53
     terlihat
    0.48
     vertrou
    0.47
     pembang
    0.47
     semua
    0.46
     melakukan
    0.45
     layak
    0.45
     stehen
    0.45
     wichtige
    0.44
     seterusnya
    0.44
    POSITIVE LOGITS
     Whether
    0.51
    uality
    0.49
     Several
    0.49
    Apple
    0.47
     To
    0.46
     A
    0.46
    Whether
    0.45
     Apple
    0.45
    Several
    0.44
     Because
    0.44
    Act Density 0.003%

    No Known Activations