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

    Neuronpedia

    INDEX
    Explanations

    Destination component, Encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guided
    0.42
    |_{\
    0.39
     explained
    0.38
     ceramic
    0.38
     পরিত্যক্ত
    0.37
     コード
    0.37
     driven
    0.37
     codes
    0.37
    ્ષ
    0.37
     Ceramic
    0.36
    POSITIVE LOGITS
    üt
    0.39
    ecz
    0.38
    otos
    0.36
    单位
    0.36
    ırs
    0.36
    bun
    0.36
     Schemes
    0.35
    โล
    0.35
    Jim
    0.35
     units
    0.34
    Act Density 0.000%

    No Known Activations