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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    1.02
    Ре
    0.70
    ેર
    0.70
    un
    0.70
     su
    0.69
     displaced
    0.66
    фи
    0.66
        
    0.65
    <0x80>
    0.64
     la
    0.64
    POSITIVE LOGITS
    ாக்கு
    0.89
    лардын
    0.87
     propositional
    0.86
     ስርዓ
    0.86
    kprop
    0.86
    ریٹر
    0.86
     matemática
    0.84
     håller
    0.84
    んにちは
    0.82
     رکھنا
    0.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.