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

    Neuronpedia

    INDEX
    Explanations

    The [START OF WORD OR CONCEPT]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     From
    0.38
     Dentistry
    0.38
     Make
    0.37
     Vite
    0.36
    ài
    0.36
    Chunks
    0.36
     Desde
    0.34
    getAll
    0.34
    ihe
    0.34
    拿出
    0.34
    POSITIVE LOGITS
    odore
    0.60
    atrical
    0.57
    oretically
    0.47
    atres
    0.47
    ка
    0.45
    lma
    0.42
    oretic
    0.40
     كان
    0.38
    א
    0.38
    matic
    0.38
    Act Density 0.154%

    No Known Activations