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

    Neuronpedia

    INDEX
    Explanations

    label design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    šky
    0.55
    untamiento
    0.48
     vayan
    0.48
     મળી
    0.47
    abba
    0.47
    erste
    0.47
     предложи
    0.47
     ឬ
    0.46
    ška
    0.46
    abi
    0.46
    POSITIVE LOGITS
    机
    0.46
    ിട
    0.44
     It
    0.43
     Finance
    0.43
    มัน
    0.43
     Hawks
    0.43
     Finances
    0.42
     Opinion
    0.41
     Opinions
    0.41
     Scholarship
    0.41
    Act Density 0.000%

    No Known Activations