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

    Neuronpedia

    INDEX
    Explanations

    service setup election

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.69
    (
    0.60
     dimensionless
    0.56
     anisotropy
    0.55
     proportional
    0.52
    1
    0.49
     pulsation
    0.49
    quela
    0.48
     indices
    0.48
    }-\
    0.47
    POSITIVE LOGITS
    ก
    0.52
    ര്‍ന്ന്
    0.52
    ı
    0.52
    onet
    0.52
    לי
    0.51
     कहें
    0.51
    𝚐
    0.50
     Banerjee
    0.50
    वायरमेंट
    0.50
    जी
    0.49
    Act Density 0.000%

    No Known Activations