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

    Neuronpedia

    INDEX
    Explanations

    un- prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TensorFlow
    0.45
    выше
    0.42
    𠃌
    0.42
    േഷൻ
    0.41
     बढ़ाकर
    0.40
    ໍ່
    0.40
    kiego
    0.40
    杰
    0.40
     AutoML
    0.39
     ఉత్పత్తి
    0.39
    POSITIVE LOGITS
     undes
    0.48
    cedented
    0.47
     undist
    0.47
    ILABLE
    0.47
     unm
    0.47
     un
    0.46
    asible
    0.46
    verläss
    0.46
     believable
    0.45
    isable
    0.44
    Act Density 0.018%

    No Known Activations