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

    Neuronpedia

    INDEX
    Explanations

    bit, plug, phase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    grey
    0.45
    罚
    0.42
    ڈنگ
    0.41
    ሯ
    0.40
    दिक
    0.39
     öd
    0.39
    THRESH
    0.38
     ära
    0.38
    hoon
    0.37
    راہ
    0.37
    POSITIVE LOGITS
     Somalia
    0.47
     Rapid
    0.44
     Mod
    0.42
     Belarus
    0.42
     GUI
    0.42
     Syria
    0.42
     распростра
    0.41
     Palau
    0.40
     Exchange
    0.40
     Metadata
    0.39
    Act Density 0.001%

    No Known Activations