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

    Neuronpedia

    INDEX
    Explanations

    categorized breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Housing
    0.41
    Missense
    0.41
    ULAR
    0.39
     kosakata
    0.38
    Bonnie
    0.38
     ôn
    0.37
     mirar
    0.37
    Pharmaceutical
    0.37
    Residential
    0.36
    酲
    0.36
    POSITIVE LOGITS
    ឌ
    0.46
    其
    0.44
     destacan
    0.44
    <h2>
    0.44
     νέα
    0.42
    <table>
    0.42
    ègre
    0.42
    plicates
    0.41
     գ
    0.41
    cluded
    0.41
    Act Density 0.060%

    No Known Activations