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

    Neuronpedia

    INDEX
    Explanations

    blue oceans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lina
    0.48
    يكل
    0.46
    ("%
    0.44
    다고
    0.43
    бята
    0.43
    病毒
    0.43
    选举
    0.42
    srand
    0.42
    特
    0.41
    ตู
    0.41
    POSITIVE LOGITS
     spout
    0.45
     fabrication
    0.45
     soaking
    0.44
    資金
    0.44
    Dip
    0.44
     unfounded
    0.44
    み
    0.44
     fertilizer
    0.43
     فایل
    0.43
     labelling
    0.42
    Act Density 0.000%

    No Known Activations