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

    Neuronpedia

    INDEX
    Explanations

    modify and edit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不少
    0.89
    some
    0.89
    riwal
    0.87
    few
    0.85
    大家的
    0.85
    不可以
    0.84
    ków
    0.84
    drž
    0.82
    elie
    0.82
    тли
    0.81
    POSITIVE LOGITS
    Hyd
    1.03
     Mag
    1.00
    Happiness
    0.99
    Hydroxy
    0.98
     holiness
    0.97
     Hyd
    0.97
     अर्
    0.97
    Ethoxy
    0.96
    TypeCode
    0.96
     Logic
    0.96
    Act Density 0.068%

    No Known Activations