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

    Neuronpedia

    INDEX
    Explanations

    database syntax and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chops
    0.52
     animations
    0.46
     officials
    0.46
     blaster
    0.44
    മ്പോൾ
    0.44
     signatures
    0.43
     appetizing
    0.43
     quirks
    0.43
     식품
    0.43
     succ
    0.43
    POSITIVE LOGITS
    Dem
    0.56
    س
    0.50
    Are
    0.50
    are
    0.49
    䒿
    0.49
    ۇ
    0.48
    ll
    0.47
    eri
    0.47
    static
    0.47
    Accessible
    0.47
    Act Density 0.004%

    No Known Activations