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

    Neuronpedia

    INDEX
    Explanations

    user query starting words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    industrie
    0.42
    dyn
    0.40
    മ്പോൾ
    0.39
    commonByteArray
    0.39
    經過
    0.39
     outbursts
    0.38
    industry
    0.37
    ره
    0.36
    reement
    0.36
     counties
    0.36
    POSITIVE LOGITS
     ucz
    0.40
     всегда
    0.38
     독
    0.37
    ChatItem
    0.37
     yak
    0.37
     опреде
    0.37
    ﱠ
    0.37
     chit
    0.36
    ಲೋ
    0.36
    전을
    0.36
    Act Density 0.001%

    No Known Activations