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

    Neuronpedia

    INDEX
    Explanations

    mathematical functions and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nervous
    0.44
     Util
    0.43
     Chemical
    0.43
     part
    0.43
    Cl
    0.41
     Application
    0.41
     Class
    0.41
     ।
    0.40
     Cl
    0.40
     Stiffness
    0.40
    POSITIVE LOGITS
     unrel
    0.39
    üşt
    0.39
     была
    0.39
     казиносу
    0.39
    인을
    0.38
    paid
    0.38
    oomla
    0.38
    ppone
    0.38
     поку
    0.38
     قرارداد
    0.37
    Act Density 0.000%

    No Known Activations