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

    Neuronpedia

    INDEX
    Explanations

    specific models and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dawn
    0.48
    Можно
    0.47
    ended
    0.45
     négoci
    0.45
    fe
    0.44
     свето
    0.44
    fine
    0.43
    off
    0.43
    machine
    0.43
    фии
    0.43
    POSITIVE LOGITS
     hydrates
    0.52
     gather
    0.48
     Investments
    0.46
     ખ
    0.45
     beverages
    0.44
    㺫
    0.44
     Gathering
    0.44
    㕣
    0.43
    াহার
    0.43
     Addresses
    0.43
    Act Density 0.000%

    No Known Activations