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

    Neuronpedia

    INDEX
    Explanations

    counting options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agglomer
    0.41
    losti
    0.38
    allele
    0.37
     दक्षता
    0.37
     ప్రశ్న
    0.36
    itochond
    0.36
    graduation
    0.36
    hezza
    0.36
    isional
    0.35
     endoscopic
    0.35
    POSITIVE LOGITS
    option
    0.46
     optio
    0.44
     Alpha
    0.42
    alpha
    0.41
     option
    0.41
     alpha
    0.38
     والش
    0.38
     Option
    0.37
     Creative
    0.37
     nuôi
    0.37
    Act Density 0.000%

    No Known Activations