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

    Neuronpedia

    INDEX
    Explanations

    clear position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     util
    0.38
    Imp
    0.37
    与
    0.37
    Brown
    0.36
    तीत
    0.36
    Cet
    0.36
     communal
    0.36
    利用
    0.35
     میرا
    0.35
     Census
    0.35
    POSITIVE LOGITS
    izziness
    0.49
     conquistar
    0.47
    ongoose
    0.46
    asmine
    0.44
    dyž
    0.43
    穹
    0.42
    AWSJavaScriptSDK
    0.42
    ხვევ
    0.41
    ledo
    0.40
    findOneAndUpdate
    0.40
    Act Density 0.003%

    No Known Activations