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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RK
    0.85
    นัก
    0.77
     Verte
    0.76
     Profil
    0.75
     SMI
    0.74
     Tutor
    0.74
     RK
    0.73
     Lo
    0.73
    味が
    0.72
     fgets
    0.72
    POSITIVE LOGITS
     અથવા
    0.88
    ાન
    0.88
     또는
    0.82
     or
    0.80
     または
    0.79
    ή
    0.79
     considerations
    0.78
     ወይም
    0.78
     किंवा
    0.77
     условии
    0.76
    Act Density 0.538%

    No Known Activations