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

    Neuronpedia

    INDEX
    Explanations

    words and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zucchero
    0.80
     sugary
    0.72
     niedrig
    0.70
    </h3>
    0.68
     Anne
    0.68
     excreted
    0.67
     Purchased
    0.67
     Aden
    0.66
     dépour
    0.64
    ̪
    0.64
    POSITIVE LOGITS
    ospheric
    0.84
    /
    0.82
    集群
    0.81
    ³/
    0.77
    ravel
    0.76
    ductory
    0.76
    based
    0.75
    μένων
    0.75
    rijk
    0.75
    riad
    0.73
    Act Density 0.403%

    No Known Activations