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

    Neuronpedia

    INDEX
    Explanations

    pro followed by certain endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     כמ
    0.44
     Journalists
    0.38
     mike
    0.38
    camiseta
    0.38
     ministers
    0.37
     compradores
    0.37
     encoders
    0.37
     이야
    0.36
     lepší
    0.36
     जबरदस्त
    0.36
    POSITIVE LOGITS
    واد
    0.43
    甫
    0.42
    ∶
    0.41
     Sozial
    0.39
     Soda
    0.38
    ⎯
    0.38
    કના
    0.38
    spa
    0.37
     GX
    0.37
    鸣
    0.37
    Act Density 0.005%

    No Known Activations