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

    Neuronpedia

    INDEX
    Explanations

    types of contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (?:
    1.98
    링
    1.95
    }*/
    1.92
     olnud
    1.91
    getParent
    1.88
    ]')
    1.87
    ും
    1.87
    𓇼
    1.85
    .}$
    1.82
    onDidChange
    1.81
    POSITIVE LOGITS
     AppleWebKit
    2.73
    ሆ
    1.92
     ren
    1.91
     Inst
    1.88
    tidak
    1.84
    mmss
    1.83
    ipak
    1.83
     pou
    1.82
    স্পতি
    1.80
    рус
    1.77
    Act Density 0.147%

    No Known Activations