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

    Neuronpedia

    INDEX
    Explanations

    Flask Python applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.64
    RO
    1.52
    原有
    1.45
    ა
    1.45
    ια
    1.43
     وعلى
    1.41
     учащихся
    1.41
    κες
    1.36
    и
    1.34
    ര
    1.34
    POSITIVE LOGITS
    সে
    1.56
     Trotz
    1.55
    er
    1.53
     sear
    1.46
     aport
    1.44
     haunting
    1.43
    はこちら
    1.38
     negozi
    1.37
     breaker
    1.34
     sosten
    1.32
    Act Density 0.002%

    No Known Activations