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

    Neuronpedia

    INDEX
    Explanations

    Giraffe and animal names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    örper
    0.43
     keny
    0.40
     Pusat
    0.40
    assertInstanceOf
    0.40
    ichtlich
    0.39
    ৎকার
    0.39
     Pies
    0.39
    бері
    0.39
     Ambedkar
    0.38
    ﮟ
    0.38
    POSITIVE LOGITS
     Gri
    0.38
     stru
    0.37
     gripped
    0.36
     shuffle
    0.35
     структур
    0.35
    Gri
    0.35
    ific
    0.34
    0.34
     Dancer
    0.34
    鐫
    0.34
    Act Density 0.004%

    No Known Activations