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

    Neuronpedia

    INDEX
    Explanations

    hardware specifics and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opaque
    0.37
    ClFN
    0.37
    expensive
    0.37
    📁
    0.36
    openstreetmap
    0.36
    🫠
    0.36
     ऑब्
    0.35
    明显
    0.35
    勇敢
    0.35
     哦
    0.35
    POSITIVE LOGITS
    owe
    0.35
     Вели
    0.34
    ティー
    0.34
    ージャー
    0.34
     ramps
    0.33
    stu
    0.33
    Resolver
    0.33
     Guarant
    0.32
     wilderness
    0.32
    ースト
    0.32
    Act Density 0.000%

    No Known Activations