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

    Neuronpedia

    INDEX
    Explanations

    https:// url

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ното
    1.04
     bepa
    1.02
     proizv
    1.01
     hypertrophy
    0.96
     hypertro
    0.95
     condicion
    0.94
     हैद
    0.93
    ಯಲ್ಲಿ
    0.92
    ным
    0.91
     слегка
    0.91
    POSITIVE LOGITS
     And
    0.95
                    
    0.94
     But
    0.89
    ://
    0.87
     In
    0.85
     You
    0.82
     Außerdem
    0.82
                   
    0.82
    can
    0.81
    MAT
    0.81
    Act Density 0.010%

    No Known Activations