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

    Neuronpedia

    INDEX
    Explanations

    colors or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    颼
    0.49
     කා
    0.47
    ل
    0.46
    arabic
    0.44
    nan
    0.44
    razier
    0.44
    大全
    0.44
     mutlaka
    0.44
    ocup
    0.43
     autism
    0.43
    POSITIVE LOGITS
    }
    0.45
     dissociation
    0.43
    」、
    0.41
    ется
    0.41
    ”、
    0.41
    响应
    0.40
    Tight
    0.40
     lysate
    0.39
     प्राथमिकी
    0.39
     covariance
    0.39
    Act Density 0.005%

    No Known Activations